{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6ZAGNRXD573TBLP25P7F5KFWHS","short_pith_number":"pith:6ZAGNRXD","schema_version":"1.0","canonical_sha256":"f64066c6e3eff730adfaebfe5ea8b63c9c8733a513e62d78ef9b2ecdd7da3cef","source":{"kind":"arxiv","id":"2606.22862","version":1},"attestation_state":"computed","paper":{"title":"Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MME","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Yanhang Li, Zexin Zhuang, Zhichao Fan","submitted_at":"2026-06-22T05:10:03Z","abstract_excerpt":"Forced chain-of-thought (CoT) is widely assumed to make vision-language models more reliable on video question answering. We propose a small three-probe evaluation recipe to test that assumption: paired accuracy across direct, CoT, answer-first, and no-video conditions; a counterfactual video-swap diagnostic over the CoT chains; and a four-rung visual-degradation ladder. Each probe is reported under both a strict and a permissive regex scorer, with multiplicity correction over a manuscript-declared primary family. Applied to Qwen2.5-VL on Video-MME subsets, the recipe returns a two-part findin"},"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":"2606.22862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T05:10:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f8a735bbe0b8f04bc122519082fdc4b772888e4f435f7ff7b6cba12b4b73b76e","abstract_canon_sha256":"47c0e42fe48ac1eb4bb724f61737f9ec85190a22dfe7654682e31b912557d1dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:02.405179Z","signature_b64":"V1r+BfcRoFMLkd5rY/u5fP8iyPwgb0u6zB5p3XOcX3O8pGiiNbESPU0jC5sp3qwzn3CoAjnCpTwmFyja4P2LBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f64066c6e3eff730adfaebfe5ea8b63c9c8733a513e62d78ef9b2ecdd7da3cef","last_reissued_at":"2026-06-23T03:14:02.404615Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:02.404615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MME","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Yanhang Li, Zexin Zhuang, Zhichao Fan","submitted_at":"2026-06-22T05:10:03Z","abstract_excerpt":"Forced chain-of-thought (CoT) is widely assumed to make vision-language models more reliable on video question answering. We propose a small three-probe evaluation recipe to test that assumption: paired accuracy across direct, CoT, answer-first, and no-video conditions; a counterfactual video-swap diagnostic over the CoT chains; and a four-rung visual-degradation ladder. Each probe is reported under both a strict and a permissive regex scorer, with multiplicity correction over a manuscript-declared primary family. Applied to Qwen2.5-VL on Video-MME subsets, the recipe returns a two-part findin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22862","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/2606.22862/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":"2606.22862","created_at":"2026-06-23T03:14:02.404675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22862v1","created_at":"2026-06-23T03:14:02.404675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22862","created_at":"2026-06-23T03:14:02.404675+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZAGNRXD573T","created_at":"2026-06-23T03:14:02.404675+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZAGNRXD573TBLP2","created_at":"2026-06-23T03:14:02.404675+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZAGNRXD","created_at":"2026-06-23T03:14:02.404675+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/6ZAGNRXD573TBLP25P7F5KFWHS","json":"https://pith.science/pith/6ZAGNRXD573TBLP25P7F5KFWHS.json","graph_json":"https://pith.science/api/pith-number/6ZAGNRXD573TBLP25P7F5KFWHS/graph.json","events_json":"https://pith.science/api/pith-number/6ZAGNRXD573TBLP25P7F5KFWHS/events.json","paper":"https://pith.science/paper/6ZAGNRXD"},"agent_actions":{"view_html":"https://pith.science/pith/6ZAGNRXD573TBLP25P7F5KFWHS","download_json":"https://pith.science/pith/6ZAGNRXD573TBLP25P7F5KFWHS.json","view_paper":"https://pith.science/paper/6ZAGNRXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22862&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZAGNRXD573TBLP25P7F5KFWHS/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZAGNRXD573TBLP25P7F5KFWHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZAGNRXD573TBLP25P7F5KFWHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZAGNRXD573TBLP25P7F5KFWHS/action/storage_attestation","attest_author":"https://pith.science/pith/6ZAGNRXD573TBLP25P7F5KFWHS/action/author_attestation","sign_citation":"https://pith.science/pith/6ZAGNRXD573TBLP25P7F5KFWHS/action/citation_signature","submit_replication":"https://pith.science/pith/6ZAGNRXD573TBLP25P7F5KFWHS/action/replication_record"}},"created_at":"2026-06-23T03:14:02.404675+00:00","updated_at":"2026-06-23T03:14:02.404675+00:00"}