{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2OIRDWB4HPTRLCRPNC7MI4FZQD","short_pith_number":"pith:2OIRDWB4","canonical_record":{"source":{"id":"2511.13026","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-17T06:25:12Z","cross_cats_sorted":[],"title_canon_sha256":"7a7586c68ee8cfa058f88ceead1a7a6bbdb8dc944dee2ba4e03e8c344f942366","abstract_canon_sha256":"6dff86d5b21bc42516c99984ee0e01c65643878402ebf23229975b5d28304e25"},"schema_version":"1.0"},"canonical_sha256":"d39111d83c3be7158a2f68bec470b980c49733b79e7a66857eed52e3f26fdeca","source":{"kind":"arxiv","id":"2511.13026","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.13026","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2511.13026v3","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.13026","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"2OIRDWB4HPTR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2OIRDWB4HPTRLCRP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2OIRDWB4","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2OIRDWB4HPTRLCRPNC7MI4FZQD","target":"record","payload":{"canonical_record":{"source":{"id":"2511.13026","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-17T06:25:12Z","cross_cats_sorted":[],"title_canon_sha256":"7a7586c68ee8cfa058f88ceead1a7a6bbdb8dc944dee2ba4e03e8c344f942366","abstract_canon_sha256":"6dff86d5b21bc42516c99984ee0e01c65643878402ebf23229975b5d28304e25"},"schema_version":"1.0"},"canonical_sha256":"d39111d83c3be7158a2f68bec470b980c49733b79e7a66857eed52e3f26fdeca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:04.623961Z","signature_b64":"rxdRb9MQYIcpd05ykBrKmGOHhJsJW/HSKITrzl1o/7dz6uiqFpHR/P88EqV+SdCeqKzyetMmJ2/UprFQBpvXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d39111d83c3be7158a2f68bec470b980c49733b79e7a66857eed52e3f26fdeca","last_reissued_at":"2026-05-17T23:39:04.623182Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:04.623182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.13026","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CZzWeKXbYdbnM6D2Rzf/lg45gqU2UpoYpJy+e6PDhvgVXaltGhR6QEIMRffVZkdOczj5It40wtiqk/fXRb7aBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:44:29.664375Z"},"content_sha256":"969a82a8d4751c3e15446fefe622fdc01bb0cc7f29eafab5c8ba3e49da212f16","schema_version":"1.0","event_id":"sha256:969a82a8d4751c3e15446fefe622fdc01bb0cc7f29eafab5c8ba3e49da212f16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2OIRDWB4HPTRLCRPNC7MI4FZQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"REVISOR lets multimodal models reflect on both text and specific video segments to improve long-form video reasoning.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boshen Xu, Hao Yin, Jian Luan, Jianzhong Ju, Jiaze Li, Jingyang Chen, Wenhui Tan, Yijing Chen, Yuxun Qu, Zhenbo Luo","submitted_at":"2025-11-17T06:25:12Z","abstract_excerpt":"Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understanding scenarios, they exhibit clear limitations. The fundamental reasons for this lie in two points: (1)long-form video understanding involves richer and more dynamic visual input, meaning rethinking only the text information is insufficient and necessitates a further rethinking process specifically targeting visual information; (2) purely text-based reflection mechanisms lack cross-modal interaction capabilities, preven"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"REVISOR enables MLLMs to collaboratively construct introspective reflection processes across textual and visual modalities, significantly enhancing their reasoning capability for long-form video understanding without requiring supplementary supervised fine-tuning or external models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That adding visual segment rethinking and cross-modal interaction during reflection will overcome the stated limitations of purely text-based reflection when applied to long-form video, and that the DADR reward will produce genuine causal alignment rather than spurious correlations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"REVISOR adds multimodal visual-text reflection and a Dual Attribution Decoupled Reward to improve long-form video reasoning in MLLMs without extra supervised fine-tuning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"REVISOR lets multimodal models reflect on both text and specific video segments to improve long-form video reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"91a18ec122b4db5b88fc65cebf7e8798e2038cdc325cce04da0abd343558da76"},"source":{"id":"2511.13026","kind":"arxiv","version":3},"verdict":{"id":"aa920106-99ce-4736-a57b-b65771deff79","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T22:16:26.945472Z","strongest_claim":"REVISOR enables MLLMs to collaboratively construct introspective reflection processes across textual and visual modalities, significantly enhancing their reasoning capability for long-form video understanding without requiring supplementary supervised fine-tuning or external models.","one_line_summary":"REVISOR adds multimodal visual-text reflection and a Dual Attribution Decoupled Reward to improve long-form video reasoning in MLLMs without extra supervised fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That adding visual segment rethinking and cross-modal interaction during reflection will overcome the stated limitations of purely text-based reflection when applied to long-form video, and that the DADR reward will produce genuine causal alignment rather than spurious correlations.","pith_extraction_headline":"REVISOR lets multimodal models reflect on both text and specific video segments to improve long-form video reasoning."},"references":{"count":66,"sample":[{"doi":"","year":2025,"title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","work_id":"40b60d06-dc1c-4799-b75d-ff1eca653049","ref_index":1,"cited_arxiv_id":"2507.19457","is_internal_anchor":true},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":2,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":null,"title":"arXiv preprint arXiv:2412.12075 , year=","work_id":"011136c4-f8a3-4d2a-a10f-3e6548f6353f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Rextime: A benchmark suite for reasoning-across-time in videos.Advances in Neural In- formation Processing Systems, 37:28662–28673, 2024","work_id":"c089f56c-97f6-4d1c-8298-aa2951cd6b1c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Sharegpt4video: Improving video understand- ing and generation with better captions.Advances in Neural Information Processing Systems, 37:19472–19495, 2024","work_id":"e2ac25e4-27d8-44d5-8a11-c4a0da16b56c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":66,"snapshot_sha256":"d08bee5f79ec35990e72941b6693e4f652b6e8ba0e5d84c2090eb03533e8e92d","internal_anchors":21},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8df5d36fdb5e71acfd9a9e2c8eba8b9182f286f7ea7a4b9d14d11bd149f7e633"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"aa920106-99ce-4736-a57b-b65771deff79"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ERJo0hOWx+wCc8uGZpwYTSxiQz9GHADhbfVKexbtxck3Cd+zwtSBwQ7wLVO3t8QIOexv6FadzDDfABDXUktwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:44:29.665517Z"},"content_sha256":"d3773b8e4a5a4b1546b759fcc26a82ced2f73239ffa396913309590064e0b6dd","schema_version":"1.0","event_id":"sha256:d3773b8e4a5a4b1546b759fcc26a82ced2f73239ffa396913309590064e0b6dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2OIRDWB4HPTRLCRPNC7MI4FZQD/bundle.json","state_url":"https://pith.science/pith/2OIRDWB4HPTRLCRPNC7MI4FZQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2OIRDWB4HPTRLCRPNC7MI4FZQD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T16:44:29Z","links":{"resolver":"https://pith.science/pith/2OIRDWB4HPTRLCRPNC7MI4FZQD","bundle":"https://pith.science/pith/2OIRDWB4HPTRLCRPNC7MI4FZQD/bundle.json","state":"https://pith.science/pith/2OIRDWB4HPTRLCRPNC7MI4FZQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2OIRDWB4HPTRLCRPNC7MI4FZQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2OIRDWB4HPTRLCRPNC7MI4FZQD","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":"6dff86d5b21bc42516c99984ee0e01c65643878402ebf23229975b5d28304e25","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-17T06:25:12Z","title_canon_sha256":"7a7586c68ee8cfa058f88ceead1a7a6bbdb8dc944dee2ba4e03e8c344f942366"},"schema_version":"1.0","source":{"id":"2511.13026","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.13026","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2511.13026v3","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.13026","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"2OIRDWB4HPTR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2OIRDWB4HPTRLCRP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2OIRDWB4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d3773b8e4a5a4b1546b759fcc26a82ced2f73239ffa396913309590064e0b6dd","target":"graph","created_at":"2026-05-17T23:39:04Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"REVISOR enables MLLMs to collaboratively construct introspective reflection processes across textual and visual modalities, significantly enhancing their reasoning capability for long-form video understanding without requiring supplementary supervised fine-tuning or external models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That adding visual segment rethinking and cross-modal interaction during reflection will overcome the stated limitations of purely text-based reflection when applied to long-form video, and that the DADR reward will produce genuine causal alignment rather than spurious correlations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"REVISOR adds multimodal visual-text reflection and a Dual Attribution Decoupled Reward to improve long-form video reasoning in MLLMs without extra supervised fine-tuning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"REVISOR lets multimodal models reflect on both text and specific video segments to improve long-form video reasoning."}],"snapshot_sha256":"91a18ec122b4db5b88fc65cebf7e8798e2038cdc325cce04da0abd343558da76"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8df5d36fdb5e71acfd9a9e2c8eba8b9182f286f7ea7a4b9d14d11bd149f7e633"},"paper":{"abstract_excerpt":"Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understanding scenarios, they exhibit clear limitations. The fundamental reasons for this lie in two points: (1)long-form video understanding involves richer and more dynamic visual input, meaning rethinking only the text information is insufficient and necessitates a further rethinking process specifically targeting visual information; (2) purely text-based reflection mechanisms lack cross-modal interaction capabilities, preven","authors_text":"Boshen Xu, Hao Yin, Jian Luan, Jianzhong Ju, Jiaze Li, Jingyang Chen, Wenhui Tan, Yijing Chen, Yuxun Qu, Zhenbo Luo","cross_cats":[],"headline":"REVISOR lets multimodal models reflect on both text and specific video segments to improve long-form video reasoning.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-17T06:25:12Z","title":"REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding"},"references":{"count":66,"internal_anchors":21,"resolved_work":66,"sample":[{"cited_arxiv_id":"2507.19457","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","work_id":"40b60d06-dc1c-4799-b75d-ff1eca653049","year":2025},{"cited_arxiv_id":"2502.13923","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"arXiv preprint arXiv:2412.12075 , year=","work_id":"011136c4-f8a3-4d2a-a10f-3e6548f6353f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Rextime: A benchmark suite for reasoning-across-time in videos.Advances in Neural In- formation Processing Systems, 37:28662–28673, 2024","work_id":"c089f56c-97f6-4d1c-8298-aa2951cd6b1c","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Sharegpt4video: Improving video understand- ing and generation with better captions.Advances in Neural Information Processing Systems, 37:19472–19495, 2024","work_id":"e2ac25e4-27d8-44d5-8a11-c4a0da16b56c","year":2024}],"snapshot_sha256":"d08bee5f79ec35990e72941b6693e4f652b6e8ba0e5d84c2090eb03533e8e92d"},"source":{"id":"2511.13026","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T22:16:26.945472Z","id":"aa920106-99ce-4736-a57b-b65771deff79","model_set":{"reader":"grok-4.3"},"one_line_summary":"REVISOR adds multimodal visual-text reflection and a Dual Attribution Decoupled Reward to improve long-form video reasoning in MLLMs without extra supervised fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"REVISOR lets multimodal models reflect on both text and specific video segments to improve long-form video reasoning.","strongest_claim":"REVISOR enables MLLMs to collaboratively construct introspective reflection processes across textual and visual modalities, significantly enhancing their reasoning capability for long-form video understanding without requiring supplementary supervised fine-tuning or external models.","weakest_assumption":"That adding visual segment rethinking and cross-modal interaction during reflection will overcome the stated limitations of purely text-based reflection when applied to long-form video, and that the DADR reward will produce genuine causal alignment rather than spurious correlations."}},"verdict_id":"aa920106-99ce-4736-a57b-b65771deff79"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:969a82a8d4751c3e15446fefe622fdc01bb0cc7f29eafab5c8ba3e49da212f16","target":"record","created_at":"2026-05-17T23:39:04Z","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":"6dff86d5b21bc42516c99984ee0e01c65643878402ebf23229975b5d28304e25","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-17T06:25:12Z","title_canon_sha256":"7a7586c68ee8cfa058f88ceead1a7a6bbdb8dc944dee2ba4e03e8c344f942366"},"schema_version":"1.0","source":{"id":"2511.13026","kind":"arxiv","version":3}},"canonical_sha256":"d39111d83c3be7158a2f68bec470b980c49733b79e7a66857eed52e3f26fdeca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d39111d83c3be7158a2f68bec470b980c49733b79e7a66857eed52e3f26fdeca","first_computed_at":"2026-05-17T23:39:04.623182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:04.623182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rxdRb9MQYIcpd05ykBrKmGOHhJsJW/HSKITrzl1o/7dz6uiqFpHR/P88EqV+SdCeqKzyetMmJ2/UprFQBpvXBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:04.623961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.13026","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:969a82a8d4751c3e15446fefe622fdc01bb0cc7f29eafab5c8ba3e49da212f16","sha256:d3773b8e4a5a4b1546b759fcc26a82ced2f73239ffa396913309590064e0b6dd"],"state_sha256":"8b36ad660c85a43387d22f61f1bd9bc5aeb8360f83c349c1062b1123ad51300f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tL3lR9ddF9Fs84F4ZiOIicxDxRcRj0+Tf1fgYi2O35fCCtEXZlS8jcY/4EZs/hNruDIE9zmckjwav7l843YBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:44:29.670248Z","bundle_sha256":"d139448ea2ce4cd2c8d7aa3476720025dc67e950039bf105d543e314e8e5c4de"}}