{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C47MOPGJX3QOK3XSCE4GMO4HFQ","short_pith_number":"pith:C47MOPGJ","schema_version":"1.0","canonical_sha256":"173ec73cc9bee0e56ef21138663b872c113c392de3e96bf717bcd21bd9a60f0d","source":{"kind":"arxiv","id":"2608.04463","version":1},"attestation_state":"computed","paper":{"title":"The Evaluator Is Part of the Experiment: Measuring Open-Ended LLM Conformity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alicia Guerra, Yibo Hu","submitted_at":"2026-08-05T05:38:34Z","abstract_excerpt":"Prior work on LLM conformity largely measures discrete answer flips under verifiable labels. Open-ended revisions require a different measurement strategy because answer quality is graded, latent, and judged imperfectly. We introduce an experimental protocol implemented across a pooled main peer-condition corpus and separately constructed decomposition corpora, allowing us to separate ordinary re-answering, candidate-content exposure, a bundled peer-presentation residual, and directional judge sensitivity to visible peer context. Across four open-weight generators and three benchmarks, all-wro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.04463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T05:38:34Z","cross_cats_sorted":[],"title_canon_sha256":"9f3d107d0a38cf2a1f2079ba5148ca74e17eac1221ef95edd48d6b1f407269b8","abstract_canon_sha256":"a4550680a680fea7092c3b9737308488020069c3e6b55a6faf2721b152a528b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:35:36.077498Z","signature_b64":"bTYJrFi5NJTZt9xEgi/TnuTC4jFn0fdFzdeVB4N4mTE0LnHJmKen2O8/EZJYot/Y0YDldRsxEJYJMuoSzg5pBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"173ec73cc9bee0e56ef21138663b872c113c392de3e96bf717bcd21bd9a60f0d","last_reissued_at":"2026-08-06T01:35:36.076073Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:35:36.076073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Evaluator Is Part of the Experiment: Measuring Open-Ended LLM Conformity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alicia Guerra, Yibo Hu","submitted_at":"2026-08-05T05:38:34Z","abstract_excerpt":"Prior work on LLM conformity largely measures discrete answer flips under verifiable labels. Open-ended revisions require a different measurement strategy because answer quality is graded, latent, and judged imperfectly. We introduce an experimental protocol implemented across a pooled main peer-condition corpus and separately constructed decomposition corpora, allowing us to separate ordinary re-answering, candidate-content exposure, a bundled peer-presentation residual, and directional judge sensitivity to visible peer context. Across four open-weight generators and three benchmarks, all-wro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04463","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.04463/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.04463","created_at":"2026-08-06T01:35:36.077865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04463v1","created_at":"2026-08-06T01:35:36.077865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04463","created_at":"2026-08-06T01:35:36.077865+00:00"},{"alias_kind":"pith_short_12","alias_value":"C47MOPGJX3QO","created_at":"2026-08-06T01:35:36.077865+00:00"},{"alias_kind":"pith_short_16","alias_value":"C47MOPGJX3QOK3XS","created_at":"2026-08-06T01:35:36.077865+00:00"},{"alias_kind":"pith_short_8","alias_value":"C47MOPGJ","created_at":"2026-08-06T01:35:36.077865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ","json":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ.json","graph_json":"https://pith.science/api/pith-number/C47MOPGJX3QOK3XSCE4GMO4HFQ/graph.json","events_json":"https://pith.science/api/pith-number/C47MOPGJX3QOK3XSCE4GMO4HFQ/events.json","paper":"https://pith.science/paper/C47MOPGJ"},"agent_actions":{"view_html":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ","download_json":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ.json","view_paper":"https://pith.science/paper/C47MOPGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04463&json=true","fetch_graph":"https://pith.science/api/pith-number/C47MOPGJX3QOK3XSCE4GMO4HFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/C47MOPGJX3QOK3XSCE4GMO4HFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ/action/storage_attestation","attest_author":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ/action/author_attestation","sign_citation":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ/action/citation_signature","submit_replication":"https://pith.science/pith/C47MOPGJX3QOK3XSCE4GMO4HFQ/action/replication_record"}},"created_at":"2026-08-06T01:35:36.077865+00:00","updated_at":"2026-08-06T01:35:36.077865+00:00"}