{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HZ5TM5YFCLSFURIJ5KPGLTCAFZ","short_pith_number":"pith:HZ5TM5YF","canonical_record":{"source":{"id":"2503.09279","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T11:25:04Z","cross_cats_sorted":[],"title_canon_sha256":"fb9efd6c0e03d1a04b5d6458f303d39afd2e36bd6d29ef930095eb7f7170a8e4","abstract_canon_sha256":"f3494c5679b4083a20f92a70827b1bb07d2f3851692e8999cf069382d0727906"},"schema_version":"1.0"},"canonical_sha256":"3e7b36770512e45a4509ea9e65cc402e5c81eec3217dbbecc560298f49c5b699","source":{"kind":"arxiv","id":"2503.09279","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09279","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09279v1","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09279","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_12","alias_value":"HZ5TM5YFCLSF","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_16","alias_value":"HZ5TM5YFCLSFURIJ","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_8","alias_value":"HZ5TM5YF","created_at":"2026-07-05T10:29:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HZ5TM5YFCLSFURIJ5KPGLTCAFZ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.09279","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T11:25:04Z","cross_cats_sorted":[],"title_canon_sha256":"fb9efd6c0e03d1a04b5d6458f303d39afd2e36bd6d29ef930095eb7f7170a8e4","abstract_canon_sha256":"f3494c5679b4083a20f92a70827b1bb07d2f3851692e8999cf069382d0727906"},"schema_version":"1.0"},"canonical_sha256":"3e7b36770512e45a4509ea9e65cc402e5c81eec3217dbbecc560298f49c5b699","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:53.209227Z","signature_b64":"GMSg1BIyLSi+kwusXNGNU5XiaUrMquKEfpBkESbN9Gwm2vSU0Dq1q/bDCQcmN2KPPpPW/cLxYa254+h3XdfICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e7b36770512e45a4509ea9e65cc402e5c81eec3217dbbecc560298f49c5b699","last_reissued_at":"2026-07-05T10:29:53.208780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:53.208780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.09279","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":"2026-07-05T10:29:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGErhjuR0wazWUBJPEl8ur6gJbp9wTJX0q6FZOBee0BPmR6q7OUuMJwk4J5SiXQWXYceUIxgrvka5GNeBielCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:30:43.224203Z"},"content_sha256":"af1f7249dca8fc3050becc8cb8aa350da44b14a02142892787f9347d4dafa54e","schema_version":"1.0","event_id":"sha256:af1f7249dca8fc3050becc8cb8aa350da44b14a02142892787f9347d4dafa54e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HZ5TM5YFCLSFURIJ5KPGLTCAFZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Luozheng Qin, Mengping Yang, Xiaomeng Yang, Zhiyu Tan","submitted_at":"2025-03-12T11:25:04Z","abstract_excerpt":"Video Detailed Captioning (VDC) is a crucial task for vision-language bridging, enabling fine-grained descriptions of complex video content. In this paper, we first comprehensively benchmark current state-of-the-art approaches and systematically identified two critical limitations: biased capability towards specific captioning aspect and misalignment with human preferences. To address these deficiencies, we propose Cockatiel, a novel three-stage training pipeline that ensembles synthetic and human-aligned training for improving VDC performance. In the first stage, we derive a scorer from a met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09279","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/2503.09279/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":"2026-07-05T10:29:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QGhlszoILxoF77bjc4d5VyCdr6o3WTJHZv5Vt9eiOon/Ta+KJlE+RjtqvKK9OrqL6jTTaEuxbTsK6CBPdSexDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:30:43.224697Z"},"content_sha256":"0dd999073f2e13b4187c1e660c0e57e73653533e52eba6e1898fec074eb6d073","schema_version":"1.0","event_id":"sha256:0dd999073f2e13b4187c1e660c0e57e73653533e52eba6e1898fec074eb6d073"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZ5TM5YFCLSFURIJ5KPGLTCAFZ/bundle.json","state_url":"https://pith.science/pith/HZ5TM5YFCLSFURIJ5KPGLTCAFZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZ5TM5YFCLSFURIJ5KPGLTCAFZ/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":"2026-08-04T22:30:43Z","links":{"resolver":"https://pith.science/pith/HZ5TM5YFCLSFURIJ5KPGLTCAFZ","bundle":"https://pith.science/pith/HZ5TM5YFCLSFURIJ5KPGLTCAFZ/bundle.json","state":"https://pith.science/pith/HZ5TM5YFCLSFURIJ5KPGLTCAFZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZ5TM5YFCLSFURIJ5KPGLTCAFZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HZ5TM5YFCLSFURIJ5KPGLTCAFZ","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":"f3494c5679b4083a20f92a70827b1bb07d2f3851692e8999cf069382d0727906","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T11:25:04Z","title_canon_sha256":"fb9efd6c0e03d1a04b5d6458f303d39afd2e36bd6d29ef930095eb7f7170a8e4"},"schema_version":"1.0","source":{"id":"2503.09279","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09279","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09279v1","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09279","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_12","alias_value":"HZ5TM5YFCLSF","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_16","alias_value":"HZ5TM5YFCLSFURIJ","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_8","alias_value":"HZ5TM5YF","created_at":"2026-07-05T10:29:53Z"}],"graph_snapshots":[{"event_id":"sha256:0dd999073f2e13b4187c1e660c0e57e73653533e52eba6e1898fec074eb6d073","target":"graph","created_at":"2026-07-05T10:29:53Z","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/2503.09279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Detailed Captioning (VDC) is a crucial task for vision-language bridging, enabling fine-grained descriptions of complex video content. In this paper, we first comprehensively benchmark current state-of-the-art approaches and systematically identified two critical limitations: biased capability towards specific captioning aspect and misalignment with human preferences. To address these deficiencies, we propose Cockatiel, a novel three-stage training pipeline that ensembles synthetic and human-aligned training for improving VDC performance. In the first stage, we derive a scorer from a met","authors_text":"Hao Li, Luozheng Qin, Mengping Yang, Xiaomeng Yang, Zhiyu Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T11:25:04Z","title":"Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09279","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:af1f7249dca8fc3050becc8cb8aa350da44b14a02142892787f9347d4dafa54e","target":"record","created_at":"2026-07-05T10:29:53Z","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":"f3494c5679b4083a20f92a70827b1bb07d2f3851692e8999cf069382d0727906","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T11:25:04Z","title_canon_sha256":"fb9efd6c0e03d1a04b5d6458f303d39afd2e36bd6d29ef930095eb7f7170a8e4"},"schema_version":"1.0","source":{"id":"2503.09279","kind":"arxiv","version":1}},"canonical_sha256":"3e7b36770512e45a4509ea9e65cc402e5c81eec3217dbbecc560298f49c5b699","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e7b36770512e45a4509ea9e65cc402e5c81eec3217dbbecc560298f49c5b699","first_computed_at":"2026-07-05T10:29:53.208780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:53.208780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GMSg1BIyLSi+kwusXNGNU5XiaUrMquKEfpBkESbN9Gwm2vSU0Dq1q/bDCQcmN2KPPpPW/cLxYa254+h3XdfICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:53.209227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09279","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af1f7249dca8fc3050becc8cb8aa350da44b14a02142892787f9347d4dafa54e","sha256:0dd999073f2e13b4187c1e660c0e57e73653533e52eba6e1898fec074eb6d073"],"state_sha256":"8eb515f3ba9bbdc6091a4bad93cfdc734e58e14b634dab7c9b6be4b63dad7e3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1u57Qcj3vwgnJhxQQStsYTnxZJsxvhKo+Zxj/NYX6klc2BORpmIblrW1IF/nvZgdU+Sz1g1Wn3A2dkx7KokMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:30:43.229446Z","bundle_sha256":"f949367b4a6557c558de0d4e0332b96fb1b9d458aae1b780631c5a3986a70c0d"}}