{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VSNBATHHLIHFBCSJ2XYVYUZIQO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"044f1d6282f0dfa1ef4d8f4e6b4350d14ce367b4ca249c250505036dbf1fa90c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T09:05:49Z","title_canon_sha256":"91ed5dd52fa1e1455ffd5682dbc8fe32ec54dccb59547b52378104c09870feb9"},"schema_version":"1.0","source":{"id":"2507.07562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07562","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07562v1","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07562","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"pith_short_12","alias_value":"VSNBATHHLIHF","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"pith_short_16","alias_value":"VSNBATHHLIHFBCSJ","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"pith_short_8","alias_value":"VSNBATHH","created_at":"2026-07-05T11:35:00Z"}],"graph_snapshots":[{"event_id":"sha256:f3af175704047913473cc4b9fc078e35e57ecae2b86d2960325e6338ea5d3168","target":"graph","created_at":"2026-07-05T11:35:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.07562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (VLMs) increasingly adopt post-training techniques such as long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL) to elicit sophisticated reasoning. While these methods exhibit synergy in language-only models, their joint effectiveness in VLMs remains uncertain. We present a systematic investigation into the distinct roles and interplay of long-CoT SFT and RL across multiple multimodal reasoning benchmarks. We find that SFT improves performance on difficult questions by in-depth, structured reasoning, but introduces verbosity and d","authors_text":"Chaofan Tao, Fei Mi, Haoli Bai, Jiannan Wu, Jierun Chen, Kaican Li, Lei Zhu, Lewei Yao, Lifeng Shang, Lu Hou, Manyi Zhang, Qun Liu, Tiezheng Yu, Xiaohui Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T09:05:49Z","title":"The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07562","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fc2dc5adfe1585d950f58af5e7fd3be2ae4a4c3c72282287601cd9a84f42afc2","target":"record","created_at":"2026-07-05T11:35:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"044f1d6282f0dfa1ef4d8f4e6b4350d14ce367b4ca249c250505036dbf1fa90c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T09:05:49Z","title_canon_sha256":"91ed5dd52fa1e1455ffd5682dbc8fe32ec54dccb59547b52378104c09870feb9"},"schema_version":"1.0","source":{"id":"2507.07562","kind":"arxiv","version":1}},"canonical_sha256":"ac9a104ce75a0e508a49d5f15c5328839d587cdbbcf88df2ea2e32a22b557cc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac9a104ce75a0e508a49d5f15c5328839d587cdbbcf88df2ea2e32a22b557cc7","first_computed_at":"2026-07-05T11:35:00.858468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:00.858468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zcH6kztHFMWEdZ35aYxL48o690XqwBQZPnTqg2r2q0lMmLqn4VLw5DQphy6qr+hgDHi1NayD/fWb/IPyUpt5Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:00.858989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc2dc5adfe1585d950f58af5e7fd3be2ae4a4c3c72282287601cd9a84f42afc2","sha256:f3af175704047913473cc4b9fc078e35e57ecae2b86d2960325e6338ea5d3168"],"state_sha256":"2ea7ac2bc47d5e98ae17ed1496fac6fe9639956939f9a77e6040b1766babb751"}