{"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"}