{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5QUREKRAZJMEP566VQEXDP2NHE","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":"b6c7ad42505f9d216e01b6ccaa4ae1b04c479ec88979fd9eded34594cda83a61","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T09:21:01Z","title_canon_sha256":"1dbbb9dd25ebd3a6d3d7a676c14ded3737cabfcb6bc8b8aabf29d5026efe7d18"},"schema_version":"1.0","source":{"id":"2407.00634","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00634","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00634v2","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00634","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"5QUREKRAZJME","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"5QUREKRAZJMEP566","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"5QUREKRA","created_at":"2026-07-05T09:10:48Z"}],"graph_snapshots":[{"event_id":"sha256:b128debb9112c8dec1dbc64d386f3cfcc9033f4d3292b2488ebd7d7e2e3a15b1","target":"graph","created_at":"2026-07-05T09:10:48Z","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/2407.00634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating fine-grained video descriptions is a fundamental challenge in video understanding. In this work, we introduce Tarsier, a family of large-scale video-language models designed to generate high-quality video descriptions. Tarsier employs CLIP-ViT to encode frames separately and then uses an LLM to model temporal relationships. Despite its simple architecture, we demonstrate that with a meticulously designed two-stage training procedure, the Tarsier models exhibit substantially stronger video description capabilities than any existing open-source model, showing a $+51.4\\%$ advantage in ","authors_text":"Haomiao Sun, Jiawei Wang, Liping Yuan, Yuchen Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T09:21:01Z","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00634","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:b8aa0bcb28523ef50c24059910a037be4ae2a90d9b311e0f3a95de01e8468c58","target":"record","created_at":"2026-07-05T09:10:48Z","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":"b6c7ad42505f9d216e01b6ccaa4ae1b04c479ec88979fd9eded34594cda83a61","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T09:21:01Z","title_canon_sha256":"1dbbb9dd25ebd3a6d3d7a676c14ded3737cabfcb6bc8b8aabf29d5026efe7d18"},"schema_version":"1.0","source":{"id":"2407.00634","kind":"arxiv","version":2}},"canonical_sha256":"ec29122a20ca5847f7deac0971bf4d393e7bb268c9e09d3360d020d0c708b9b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec29122a20ca5847f7deac0971bf4d393e7bb268c9e09d3360d020d0c708b9b6","first_computed_at":"2026-07-05T09:10:48.634940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:48.634940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7VSrVGMHhTBzV61nWheiMVMxolL6+Qh/AwkA5HiNunTOh6XtTyyyLjLFCyMPlVF33ptqmog4aSUnQWBhTHNaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:48.635389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00634","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8aa0bcb28523ef50c24059910a037be4ae2a90d9b311e0f3a95de01e8468c58","sha256:b128debb9112c8dec1dbc64d386f3cfcc9033f4d3292b2488ebd7d7e2e3a15b1"],"state_sha256":"8158c066df92371fa187e1fdb09e4cb09dda3d233153b97e15deec957a667765"}