mirror of
https://github.com/Imbad0202/academic-research-skills.git
synced 2026-09-14 13:51:17 +08:00
Edward Cheng-I Wu
6b7ee6dcae
* fix: Astra request compatibility, no-delegation citation transport, hedge/quota prompt repairs, audit provenance (#823 #824 #825 #826) #823 — OpenAI request builders (smoke entrypoint + documented example) drop `temperature`, which GPT-6 Astra rejects; the per-model effort vocabulary lives in scripts/cross_model_verification/openai_effort_guard.sh, sourced by both, and an unsupported explicit Astra value fails before curl. Hermetic fake-curl test runs both surfaces. #824 — the contained Codex citation transport rejects effort=ultra with REASONING_EFFORT_REQUIRES_DELEGATION before detection/auth/tempdir/launch on both entry paths (codex-cli 0.153.4 defines ultra as the multiAgentMode replacement). Model-independent by design. #825 — hedging can no longer rescue an unsupported claim (writer recovery tree, CER fallback row, temporal rule 5 in writer + both compiler mirrors, writer contract D2); universal prose quotas in the writer, compilers, writing_quality_check.md, academic-paper/SKILL.md, and contract D6 become diagnostics subordinate to author/venue requirements. Audit inventory corrected in place; held-out seed evals/heldout/unsupported_claim_recovery (NOT_RUN) registered. #826 — run_codex_audit.sh pins gpt-6-astra/xhigh and records both in a new sidecar `model` block; claim_audit_pipeline binds an unknown judge identity to a run-local cache key (no cross-run reuse) instead of defaulting to gpt-5.5-xhigh. Review: /simplify (4 angles), codex gpt-5.6-sol xhigh 2 rounds (r1: 1 P1 + 1 P2 + 2 P3 fixed; r2: 0 P1/P2), /security-review 0 findings; all 102 spec-consistency steps + pytest manifest replayed locally. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BNKiXpdHx1T5F5RbXT2Ueu * docs(claude): record the #824 ultra reversal in the v3.21.2 key-additions line The v3.21.2 bullet still said the contained Codex citation transport accepts ultra; #824 on this branch rejects it as a delegation request. Add the reversal so the live instruction surface matches the transport. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01K7emV5r2aqZDJzAyYVuuDo --------- Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
88 lines
3.6 KiB
JSON
88 lines
3.6 KiB
JSON
{
|
|
"contract_id": "academic_paper/writer_full/v1",
|
|
"mode": "writer_full",
|
|
"stage": "writer_full_drafting",
|
|
"baseline_version": "v3.6.6",
|
|
"acceptance_dimensions": [
|
|
{
|
|
"id": "D1",
|
|
"name": "section_completeness",
|
|
"description": "Every section in the Structure Architect's approved outline is written; no [MATERIAL GAP] placeholders remain unresolved at handoff to citation_compliance.",
|
|
"priority": "mandatory"
|
|
},
|
|
{
|
|
"id": "D2",
|
|
"name": "citation_density",
|
|
"description": "Every factual claim carries at least one citation; uncited factual claims either gain a source, are omitted, or are marked [MATERIAL GAP] for author review; hedging language alone does not satisfy this dimension. Exception (#548): absence/novelty claims cannot cite a source for an absence — they satisfy this dimension via documented-search provenance in the bounded form plus a citation to the named nearest prior work where adjacent work exists; the explicit absence-of-adjacent-work statement satisfies it otherwise.",
|
|
"priority": "mandatory"
|
|
},
|
|
{
|
|
"id": "D3",
|
|
"name": "argument_blueprint_fidelity",
|
|
"description": "Each section follows the CER chains delivered by argument_builder_agent (the Argument Blueprint runtime artefact); topic sentences match the claim, evidence cites assigned sources, and explanation links back to the section purpose. The Argument Blueprint, not the contract, is the source of CER chains.",
|
|
"priority": "mandatory"
|
|
},
|
|
{
|
|
"id": "D4",
|
|
"name": "total_word_count",
|
|
"description": "Final draft total stays within plus or minus 10 percent of the target declared in the Paper Configuration Record.",
|
|
"priority": "high"
|
|
},
|
|
{
|
|
"id": "D5",
|
|
"name": "per_section_word_count",
|
|
"description": "Each section stays within plus or minus 15 percent of the per-section allocation declared in the Paper Configuration Record.",
|
|
"priority": "high"
|
|
},
|
|
{
|
|
"id": "D6",
|
|
"name": "paragraph_structure",
|
|
"description": "Body paragraphs serve their section's purpose with a clear point, adequate cited support, explanation, and linkage, judged by clarity and evidential support rather than a TEEL percentage or length preset; author and venue requirements take priority. Inter-section transitions present.",
|
|
"priority": "normal"
|
|
},
|
|
{
|
|
"id": "D7",
|
|
"name": "register_consistency",
|
|
"description": "Academic register holds throughout; no colloquial mixing; discipline-appropriate phrasing per the Paper Configuration Record.",
|
|
"priority": "normal"
|
|
}
|
|
],
|
|
"pre_commitment_artifacts": {
|
|
"acceptance_criteria_paraphrase": {
|
|
"minimum_dimensions": "all"
|
|
}
|
|
},
|
|
"failure_conditions": [
|
|
{
|
|
"condition_id": "F1",
|
|
"severity": 90,
|
|
"expression": "any mandatory dimension scores 'block'",
|
|
"action": "writer_decision=escalate_to_evaluator"
|
|
},
|
|
{
|
|
"condition_id": "F4",
|
|
"severity": 75,
|
|
"expression": "any mandatory dimension scores 'warn'",
|
|
"action": "writer_decision=revise_in_phase_4b"
|
|
},
|
|
{
|
|
"condition_id": "F2",
|
|
"severity": 60,
|
|
"expression": "any high-priority dimension scores 'block'",
|
|
"action": "writer_decision=revise_in_phase_4b"
|
|
},
|
|
{
|
|
"condition_id": "F3",
|
|
"severity": 40,
|
|
"expression": "any high-priority dimension scores 'warn'",
|
|
"action": "writer_decision=revise_in_phase_4b"
|
|
},
|
|
{
|
|
"condition_id": "F0",
|
|
"severity": 10,
|
|
"expression": "every mandatory dimension scores 'pass'",
|
|
"action": "writer_decision=accept"
|
|
}
|
|
]
|
|
}
|