{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WDZOQVVNWAQLZEAO2JTLSSXCN2","short_pith_number":"pith:WDZOQVVN","canonical_record":{"source":{"id":"2501.07888","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T06:54:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a148cb8f76b6b263a06b3e34bf354f17e16a6a705eb5f354943d3d0e03c6647","abstract_canon_sha256":"294c1d0933a2666993702296e6e19004e5c3076b8909927d641c22934ba7022e"},"schema_version":"1.0"},"canonical_sha256":"b0f2e856adb020bc900ed266b94ae26ebf90d9262e5e731a1b956b787ac4fa2c","source":{"kind":"arxiv","id":"2501.07888","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07888","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07888v3","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07888","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"WDZOQVVNWAQL","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"WDZOQVVNWAQLZEAO","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"WDZOQVVN","created_at":"2026-07-05T10:04:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WDZOQVVNWAQLZEAO2JTLSSXCN2","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07888","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T06:54:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a148cb8f76b6b263a06b3e34bf354f17e16a6a705eb5f354943d3d0e03c6647","abstract_canon_sha256":"294c1d0933a2666993702296e6e19004e5c3076b8909927d641c22934ba7022e"},"schema_version":"1.0"},"canonical_sha256":"b0f2e856adb020bc900ed266b94ae26ebf90d9262e5e731a1b956b787ac4fa2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:41.818541Z","signature_b64":"gOnIzSxWljiAE1TT1r7LHoNOOnnqK2lHcHsLheOYhQLiQILsedOsZH4Mqz2wZqgCEoMGBEtYEWITOeomaBzQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0f2e856adb020bc900ed266b94ae26ebf90d9262e5e731a1b956b787ac4fa2c","last_reissued_at":"2026-07-05T10:04:41.818083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:41.818083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07888","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":"2026-07-05T10:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8H9Wjdg+3SRqhAqQIxt8LqaBLYp6qHVGIlzJ3UX8paPvKoFMBEazS6gY+QZFHGpO73qpXcAPRuWBkoqRa6qBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:01:16.826706Z"},"content_sha256":"b6516dd44a3ce5e0bd598d1be62563088809c432ed870c886fd8de1522637d73","schema_version":"1.0","event_id":"sha256:b6516dd44a3ce5e0bd598d1be62563088809c432ed870c886fd8de1522637d73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WDZOQVVNWAQLZEAO2JTLSSXCN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haomiao Sun, Jiawei Wang, Liping Yuan, Yuan Lin, Yuchen Zhang","submitted_at":"2025-01-14T06:54:39Z","abstract_excerpt":"We introduce Tarsier2, a state-of-the-art large vision-language model (LVLM) designed for generating detailed and accurate video descriptions, while also exhibiting superior general video understanding capabilities. Tarsier2 achieves significant advancements through three key upgrades: (1) Scaling pre-training data from 11M to 40M video-text pairs, enriching both volume and diversity; (2) Performing fine-grained temporal alignment during supervised fine-tuning; (3) Using model-based sampling to automatically construct preference data and applying DPO training for optimization. Extensive experi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07888","kind":"arxiv","version":3},"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/2501.07888/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":"2026-07-05T10:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oq9OZ+txG2rzxdKR/CQCJGK6nAR/FWCfnvHMyV5+VORK1C5oNO9+g5td5hYh1X6lEyEuVTfGH8xg/IbYGhupCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:01:16.827293Z"},"content_sha256":"3aa5728c9d0b26822ec8a3b15d1571b5baa32c7cf87a33042e2bf3c52a1e9371","schema_version":"1.0","event_id":"sha256:3aa5728c9d0b26822ec8a3b15d1571b5baa32c7cf87a33042e2bf3c52a1e9371"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WDZOQVVNWAQLZEAO2JTLSSXCN2/bundle.json","state_url":"https://pith.science/pith/WDZOQVVNWAQLZEAO2JTLSSXCN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WDZOQVVNWAQLZEAO2JTLSSXCN2/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":"2026-08-06T02:01:16Z","links":{"resolver":"https://pith.science/pith/WDZOQVVNWAQLZEAO2JTLSSXCN2","bundle":"https://pith.science/pith/WDZOQVVNWAQLZEAO2JTLSSXCN2/bundle.json","state":"https://pith.science/pith/WDZOQVVNWAQLZEAO2JTLSSXCN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WDZOQVVNWAQLZEAO2JTLSSXCN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WDZOQVVNWAQLZEAO2JTLSSXCN2","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":"294c1d0933a2666993702296e6e19004e5c3076b8909927d641c22934ba7022e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T06:54:39Z","title_canon_sha256":"0a148cb8f76b6b263a06b3e34bf354f17e16a6a705eb5f354943d3d0e03c6647"},"schema_version":"1.0","source":{"id":"2501.07888","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07888","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07888v3","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07888","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"WDZOQVVNWAQL","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"WDZOQVVNWAQLZEAO","created_at":"2026-07-05T10:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"WDZOQVVN","created_at":"2026-07-05T10:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:3aa5728c9d0b26822ec8a3b15d1571b5baa32c7cf87a33042e2bf3c52a1e9371","target":"graph","created_at":"2026-07-05T10:04:41Z","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/2501.07888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Tarsier2, a state-of-the-art large vision-language model (LVLM) designed for generating detailed and accurate video descriptions, while also exhibiting superior general video understanding capabilities. Tarsier2 achieves significant advancements through three key upgrades: (1) Scaling pre-training data from 11M to 40M video-text pairs, enriching both volume and diversity; (2) Performing fine-grained temporal alignment during supervised fine-tuning; (3) Using model-based sampling to automatically construct preference data and applying DPO training for optimization. Extensive experi","authors_text":"Haomiao Sun, Jiawei Wang, Liping Yuan, Yuan Lin, Yuchen Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T06:54:39Z","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07888","kind":"arxiv","version":3},"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:b6516dd44a3ce5e0bd598d1be62563088809c432ed870c886fd8de1522637d73","target":"record","created_at":"2026-07-05T10:04:41Z","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":"294c1d0933a2666993702296e6e19004e5c3076b8909927d641c22934ba7022e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T06:54:39Z","title_canon_sha256":"0a148cb8f76b6b263a06b3e34bf354f17e16a6a705eb5f354943d3d0e03c6647"},"schema_version":"1.0","source":{"id":"2501.07888","kind":"arxiv","version":3}},"canonical_sha256":"b0f2e856adb020bc900ed266b94ae26ebf90d9262e5e731a1b956b787ac4fa2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0f2e856adb020bc900ed266b94ae26ebf90d9262e5e731a1b956b787ac4fa2c","first_computed_at":"2026-07-05T10:04:41.818083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:41.818083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gOnIzSxWljiAE1TT1r7LHoNOOnnqK2lHcHsLheOYhQLiQILsedOsZH4Mqz2wZqgCEoMGBEtYEWITOeomaBzQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:41.818541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07888","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6516dd44a3ce5e0bd598d1be62563088809c432ed870c886fd8de1522637d73","sha256:3aa5728c9d0b26822ec8a3b15d1571b5baa32c7cf87a33042e2bf3c52a1e9371"],"state_sha256":"88134dbe49de28befb74cd14a1925e7f660c2af920d9908f4b2a4493b31b58e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mFyyYjmi4rqkrhm0cRWu2udgksX1GsWTMnWvFb/TyyJC4f0HlxDX87JW99cDwEe8j6ceLwytthBoTTArnxg4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:01:16.833811Z","bundle_sha256":"6a0c5bab8e9e38b9e3e80637ddb907dc6b43a891637a85c7c7afb3f69aa82ca9"}}