{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IIC5QNTWVSX7MVAB3BSZEH2NOK","short_pith_number":"pith:IIC5QNTW","canonical_record":{"source":{"id":"2511.19436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:59:56Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"3b903e4890294a58d76ae116254aceea441d4dea40b7c5271085d32958230e2a","abstract_canon_sha256":"bf2cd626f1557da3762998951a70c26dba33416aee1b4acaf4a1b2a76380fd87"},"schema_version":"1.0"},"canonical_sha256":"4205d83676acaff65401d865921f4d72b2478f83c91db97776f7a5f339779c32","source":{"kind":"arxiv","id":"2511.19436","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19436","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19436v2","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19436","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"IIC5QNTWVSX7","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"IIC5QNTWVSX7MVAB","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"IIC5QNTW","created_at":"2026-08-12T01:21:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IIC5QNTWVSX7MVAB3BSZEH2NOK","target":"record","payload":{"canonical_record":{"source":{"id":"2511.19436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:59:56Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"3b903e4890294a58d76ae116254aceea441d4dea40b7c5271085d32958230e2a","abstract_canon_sha256":"bf2cd626f1557da3762998951a70c26dba33416aee1b4acaf4a1b2a76380fd87"},"schema_version":"1.0"},"canonical_sha256":"4205d83676acaff65401d865921f4d72b2478f83c91db97776f7a5f339779c32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:21:21.652981Z","signature_b64":"tmkLO9pHJumXgcRxVZQkN7a2jR20mITDS/NnX8XZ7KHzb/5z1lcpJ/YqvIaQCDAD370aTRJGhbbPOXVeFIz/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4205d83676acaff65401d865921f4d72b2478f83c91db97776f7a5f339779c32","last_reissued_at":"2026-08-12T01:21:21.651029Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:21:21.651029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.19436","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-12T01:21:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lbHKDbMHt9fpTZgREEWyIq6TSXabrOy04/gq+S0ZUCoXzKuBMyVIh6xuU3qPz7lTKJyMQsbU5Dq8i3j44JuBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:12:53.024614Z"},"content_sha256":"a76aa0c2481dd0224b4fcd57fc444f82a9933ef81c2805f6fbc0694a959f0bcc","schema_version":"1.0","event_id":"sha256:a76aa0c2481dd0224b4fcd57fc444f82a9933ef81c2805f6fbc0694a959f0bcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IIC5QNTWVSX7MVAB3BSZEH2NOK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jiangyang Li, Jizhou Han, Qiang Wang, SongLin Dong, Xinyuan Gao, Yihong Gong, Yuhang He, Zhiheng Ma","submitted_at":"2025-11-24T18:59:56Z","abstract_excerpt":"Existing Video Detailed Captioning (VDC) methods predominantly rely on costly human annotations or distillation from powerful proprietary models, creating a dependency on external supervision. In this paper, we propose VDC-Agent, an autonomous self-evolving framework that empowers a single Multimodal Large Language Model (MLLM) to generate and refine high-quality captions through principle-guided self-reflection. To overcome the inference latency inherent in iterative refinement, we further propose to internalize this reflective capability into the model. Specifically, we construct VDC-Agent-1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19436","kind":"arxiv","version":2},"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/2511.19436/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-12T01:21:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tMgF5Y/X4oqOQQ7R/12HKgYdr0fRVrPYLZagTXY3dwB5mHFgdYP9QbFpreh+6Oq9oAvGI8e42H8UcUfw53RhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:12:53.025099Z"},"content_sha256":"a3a713c90ef34e72fab7730abae58efd36694d9631cec08ad70228cf3412c9a6","schema_version":"1.0","event_id":"sha256:a3a713c90ef34e72fab7730abae58efd36694d9631cec08ad70228cf3412c9a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IIC5QNTWVSX7MVAB3BSZEH2NOK/bundle.json","state_url":"https://pith.science/pith/IIC5QNTWVSX7MVAB3BSZEH2NOK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IIC5QNTWVSX7MVAB3BSZEH2NOK/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":"2026-08-18T19:12:53Z","links":{"resolver":"https://pith.science/pith/IIC5QNTWVSX7MVAB3BSZEH2NOK","bundle":"https://pith.science/pith/IIC5QNTWVSX7MVAB3BSZEH2NOK/bundle.json","state":"https://pith.science/pith/IIC5QNTWVSX7MVAB3BSZEH2NOK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IIC5QNTWVSX7MVAB3BSZEH2NOK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IIC5QNTWVSX7MVAB3BSZEH2NOK","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":"bf2cd626f1557da3762998951a70c26dba33416aee1b4acaf4a1b2a76380fd87","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:59:56Z","title_canon_sha256":"3b903e4890294a58d76ae116254aceea441d4dea40b7c5271085d32958230e2a"},"schema_version":"1.0","source":{"id":"2511.19436","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19436","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19436v2","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19436","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"IIC5QNTWVSX7","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"IIC5QNTWVSX7MVAB","created_at":"2026-08-12T01:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"IIC5QNTW","created_at":"2026-08-12T01:21:21Z"}],"graph_snapshots":[{"event_id":"sha256:a3a713c90ef34e72fab7730abae58efd36694d9631cec08ad70228cf3412c9a6","target":"graph","created_at":"2026-08-12T01:21:21Z","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/2511.19436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Video Detailed Captioning (VDC) methods predominantly rely on costly human annotations or distillation from powerful proprietary models, creating a dependency on external supervision. In this paper, we propose VDC-Agent, an autonomous self-evolving framework that empowers a single Multimodal Large Language Model (MLLM) to generate and refine high-quality captions through principle-guided self-reflection. To overcome the inference latency inherent in iterative refinement, we further propose to internalize this reflective capability into the model. Specifically, we construct VDC-Agent-1","authors_text":"Jiangyang Li, Jizhou Han, Qiang Wang, SongLin Dong, Xinyuan Gao, Yihong Gong, Yuhang He, Zhiheng Ma","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:59:56Z","title":"VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19436","kind":"arxiv","version":2},"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:a76aa0c2481dd0224b4fcd57fc444f82a9933ef81c2805f6fbc0694a959f0bcc","target":"record","created_at":"2026-08-12T01:21:21Z","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":"bf2cd626f1557da3762998951a70c26dba33416aee1b4acaf4a1b2a76380fd87","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:59:56Z","title_canon_sha256":"3b903e4890294a58d76ae116254aceea441d4dea40b7c5271085d32958230e2a"},"schema_version":"1.0","source":{"id":"2511.19436","kind":"arxiv","version":2}},"canonical_sha256":"4205d83676acaff65401d865921f4d72b2478f83c91db97776f7a5f339779c32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4205d83676acaff65401d865921f4d72b2478f83c91db97776f7a5f339779c32","first_computed_at":"2026-08-12T01:21:21.651029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:21:21.651029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tmkLO9pHJumXgcRxVZQkN7a2jR20mITDS/NnX8XZ7KHzb/5z1lcpJ/YqvIaQCDAD370aTRJGhbbPOXVeFIz/BA==","signature_status":"signed_v1","signed_at":"2026-08-12T01:21:21.652981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.19436","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a76aa0c2481dd0224b4fcd57fc444f82a9933ef81c2805f6fbc0694a959f0bcc","sha256:a3a713c90ef34e72fab7730abae58efd36694d9631cec08ad70228cf3412c9a6"],"state_sha256":"05dd52cdcf6dc3c531ee006eac22263c91f150a7f250bc2c00d5f64faf9d0fbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7bl0CABgq3rkKEqvZVwOY+mF3S+AaQcyH9esl/K5QHEniqS91h3Pc2a70SUAAtrJFGu4+JSz5ehUkeHkfFpuBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:12:53.028411Z","bundle_sha256":"fafec24b1cf344a7c4d7002f05041f056741cbb4974689171d4f2dab91ac8820"}}