{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YJVRCFWZJIN27JVA4LZJDBTW4A","short_pith_number":"pith:YJVRCFWZ","canonical_record":{"source":{"id":"2507.01492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T08:51:45Z","cross_cats_sorted":[],"title_canon_sha256":"0ffcdcd37e2ccc37f1c19c95b11a6753e2d508d4a0acc49d1cbac7c43bb1ffd2","abstract_canon_sha256":"54b2934b67d15e9c650a869fd9a6449908b8782cec7837118396b801491ee68a"},"schema_version":"1.0"},"canonical_sha256":"c26b1116d94a1bafa6a0e2f2918676e01192adf24a2cb54eba936c8f8ea6f2a7","source":{"kind":"arxiv","id":"2507.01492","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01492","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01492v1","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01492","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"YJVRCFWZJIN2","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"YJVRCFWZJIN27JVA","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"YJVRCFWZ","created_at":"2026-07-05T11:30:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YJVRCFWZJIN27JVA4LZJDBTW4A","target":"record","payload":{"canonical_record":{"source":{"id":"2507.01492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T08:51:45Z","cross_cats_sorted":[],"title_canon_sha256":"0ffcdcd37e2ccc37f1c19c95b11a6753e2d508d4a0acc49d1cbac7c43bb1ffd2","abstract_canon_sha256":"54b2934b67d15e9c650a869fd9a6449908b8782cec7837118396b801491ee68a"},"schema_version":"1.0"},"canonical_sha256":"c26b1116d94a1bafa6a0e2f2918676e01192adf24a2cb54eba936c8f8ea6f2a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:49.870941Z","signature_b64":"MjdCSpq0W0N3E8qbrSbFnExr3c4uePKKiYneZX6lxzk07AXlbmMB8t0sOGZpmOVakjL/cnT4otdvLSYj7ba6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c26b1116d94a1bafa6a0e2f2918676e01192adf24a2cb54eba936c8f8ea6f2a7","last_reissued_at":"2026-07-05T11:30:49.869609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:49.869609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.01492","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9e5T5QcP2qwztux2kVWjIWSQFWFZNo1vFDbcauwfPZElOXsjZMus2vSI54sE+R42EYe0RkxG/+HrDpI7fHXwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:27:11.894499Z"},"content_sha256":"3995f5c214fe628d95086e09d46012a276151ece07b67c96f3fe106e84d65666","schema_version":"1.0","event_id":"sha256:3995f5c214fe628d95086e09d46012a276151ece07b67c96f3fe106e84d65666"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YJVRCFWZJIN27JVA4LZJDBTW4A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AVC-DPO: Aligned Video Captioning via Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengyi Li, Jiyang Tang, Wayne Xin Zhao, Yifan Du","submitted_at":"2025-07-02T08:51:45Z","abstract_excerpt":"Although video multimodal large language models (video MLLMs) have achieved substantial progress in video captioning tasks, it remains challenging to adjust the focal emphasis of video captions according to human preferences. To address this limitation, we propose Aligned Video Captioning via Direct Preference Optimization (AVC-DPO), a post-training framework designed to enhance captioning capabilities in video MLLMs through preference alignment. Our approach designs enhanced prompts that specifically target temporal dynamics and spatial information-two key factors that humans care about when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01492","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/2507.01492/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":"2026-07-05T11:30:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IWx8WSGnBvCOy3uuNh6bdoy5jzBML5DAkApelnxA8bqLtbutuNhNP8hUlDvvm1/JE5JGx3AICjAijMd5FIWEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:27:11.894871Z"},"content_sha256":"035a19e466614d27fd699b1a7db36b46a151c30a89f66c42d7eeb074164e4251","schema_version":"1.0","event_id":"sha256:035a19e466614d27fd699b1a7db36b46a151c30a89f66c42d7eeb074164e4251"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJVRCFWZJIN27JVA4LZJDBTW4A/bundle.json","state_url":"https://pith.science/pith/YJVRCFWZJIN27JVA4LZJDBTW4A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJVRCFWZJIN27JVA4LZJDBTW4A/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":"2026-08-18T08:27:11Z","links":{"resolver":"https://pith.science/pith/YJVRCFWZJIN27JVA4LZJDBTW4A","bundle":"https://pith.science/pith/YJVRCFWZJIN27JVA4LZJDBTW4A/bundle.json","state":"https://pith.science/pith/YJVRCFWZJIN27JVA4LZJDBTW4A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJVRCFWZJIN27JVA4LZJDBTW4A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YJVRCFWZJIN27JVA4LZJDBTW4A","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":"54b2934b67d15e9c650a869fd9a6449908b8782cec7837118396b801491ee68a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T08:51:45Z","title_canon_sha256":"0ffcdcd37e2ccc37f1c19c95b11a6753e2d508d4a0acc49d1cbac7c43bb1ffd2"},"schema_version":"1.0","source":{"id":"2507.01492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01492","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01492v1","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01492","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"YJVRCFWZJIN2","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"YJVRCFWZJIN27JVA","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"YJVRCFWZ","created_at":"2026-07-05T11:30:49Z"}],"graph_snapshots":[{"event_id":"sha256:035a19e466614d27fd699b1a7db36b46a151c30a89f66c42d7eeb074164e4251","target":"graph","created_at":"2026-07-05T11:30:49Z","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/2507.01492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although video multimodal large language models (video MLLMs) have achieved substantial progress in video captioning tasks, it remains challenging to adjust the focal emphasis of video captions according to human preferences. To address this limitation, we propose Aligned Video Captioning via Direct Preference Optimization (AVC-DPO), a post-training framework designed to enhance captioning capabilities in video MLLMs through preference alignment. Our approach designs enhanced prompts that specifically target temporal dynamics and spatial information-two key factors that humans care about when ","authors_text":"Hengyi Li, Jiyang Tang, Wayne Xin Zhao, Yifan Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T08:51:45Z","title":"AVC-DPO: Aligned Video Captioning via Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01492","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":"sha256:3995f5c214fe628d95086e09d46012a276151ece07b67c96f3fe106e84d65666","target":"record","created_at":"2026-07-05T11:30:49Z","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":"54b2934b67d15e9c650a869fd9a6449908b8782cec7837118396b801491ee68a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T08:51:45Z","title_canon_sha256":"0ffcdcd37e2ccc37f1c19c95b11a6753e2d508d4a0acc49d1cbac7c43bb1ffd2"},"schema_version":"1.0","source":{"id":"2507.01492","kind":"arxiv","version":1}},"canonical_sha256":"c26b1116d94a1bafa6a0e2f2918676e01192adf24a2cb54eba936c8f8ea6f2a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c26b1116d94a1bafa6a0e2f2918676e01192adf24a2cb54eba936c8f8ea6f2a7","first_computed_at":"2026-07-05T11:30:49.869609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:49.869609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MjdCSpq0W0N3E8qbrSbFnExr3c4uePKKiYneZX6lxzk07AXlbmMB8t0sOGZpmOVakjL/cnT4otdvLSYj7ba6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:49.870941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3995f5c214fe628d95086e09d46012a276151ece07b67c96f3fe106e84d65666","sha256:035a19e466614d27fd699b1a7db36b46a151c30a89f66c42d7eeb074164e4251"],"state_sha256":"26ef7dcaaead532a8a037c1358ec4ba776c507507688a0a4d0818ee8bf24340d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7MhtnQn96vGk66UHFK/KEsQdjJ7jI+9fau9asE8wra6erCtfmt5zgruSZtW+k9EZhFr6HCVgdHa2o82kiW37DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:27:11.897496Z","bundle_sha256":"625cdc60ba2237ee75336a12a736c253d900c5c76d2bd8e93b1d0d44f5598a95"}}