{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5QUREKRAZJMEP566VQEXDP2NHE","short_pith_number":"pith:5QUREKRA","canonical_record":{"source":{"id":"2407.00634","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T09:21:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1dbbb9dd25ebd3a6d3d7a676c14ded3737cabfcb6bc8b8aabf29d5026efe7d18","abstract_canon_sha256":"b6c7ad42505f9d216e01b6ccaa4ae1b04c479ec88979fd9eded34594cda83a61"},"schema_version":"1.0"},"canonical_sha256":"ec29122a20ca5847f7deac0971bf4d393e7bb268c9e09d3360d020d0c708b9b6","source":{"kind":"arxiv","id":"2407.00634","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5QUREKRAZJMEP566VQEXDP2NHE","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00634","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T09:21:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1dbbb9dd25ebd3a6d3d7a676c14ded3737cabfcb6bc8b8aabf29d5026efe7d18","abstract_canon_sha256":"b6c7ad42505f9d216e01b6ccaa4ae1b04c479ec88979fd9eded34594cda83a61"},"schema_version":"1.0"},"canonical_sha256":"ec29122a20ca5847f7deac0971bf4d393e7bb268c9e09d3360d020d0c708b9b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:48.635389Z","signature_b64":"7VSrVGMHhTBzV61nWheiMVMxolL6+Qh/AwkA5HiNunTOh6XtTyyyLjLFCyMPlVF33ptqmog4aSUnQWBhTHNaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec29122a20ca5847f7deac0971bf4d393e7bb268c9e09d3360d020d0c708b9b6","last_reissued_at":"2026-07-05T09:10:48.634940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:48.634940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00634","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eaQZcdRjvCPyFnl/hQJFYrdjjYK1HCrNXrvb69dT6zNMyAkh5L9MT4e0DwcOk7GR0YlnSpASJxGXYS3ee6oMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:43:42.194589Z"},"content_sha256":"b8aa0bcb28523ef50c24059910a037be4ae2a90d9b311e0f3a95de01e8468c58","schema_version":"1.0","event_id":"sha256:b8aa0bcb28523ef50c24059910a037be4ae2a90d9b311e0f3a95de01e8468c58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5QUREKRAZJMEP566VQEXDP2NHE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haomiao Sun, Jiawei Wang, Liping Yuan, Yuchen Zhang","submitted_at":"2024-06-30T09:21:01Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00634","kind":"arxiv","version":2},"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/2407.00634/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":"2026-07-05T09:10:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oiAcoeJpiCw1Q8K6P1IUZP9STm/x+u4syMvzrst29spvg1zqfohvMd6vGlFtkNPZep3mN/mcMZQ0CP/wPRdEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:43:42.195517Z"},"content_sha256":"b128debb9112c8dec1dbc64d386f3cfcc9033f4d3292b2488ebd7d7e2e3a15b1","schema_version":"1.0","event_id":"sha256:b128debb9112c8dec1dbc64d386f3cfcc9033f4d3292b2488ebd7d7e2e3a15b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QUREKRAZJMEP566VQEXDP2NHE/bundle.json","state_url":"https://pith.science/pith/5QUREKRAZJMEP566VQEXDP2NHE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QUREKRAZJMEP566VQEXDP2NHE/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":"2026-08-04T18:43:42Z","links":{"resolver":"https://pith.science/pith/5QUREKRAZJMEP566VQEXDP2NHE","bundle":"https://pith.science/pith/5QUREKRAZJMEP566VQEXDP2NHE/bundle.json","state":"https://pith.science/pith/5QUREKRAZJMEP566VQEXDP2NHE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QUREKRAZJMEP566VQEXDP2NHE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skBHj825/wj8l7TbOOhDxXmz4Hpn6CObRnnLzedWRSifTHbQPhS+uan0p1Wv6u7YMC1ch3/F8lu0RBaxXtFnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T18:43:42.278758Z","bundle_sha256":"bcf8379b93a9ebebe6732448b7f9e8899ca0e54ce36b483516e6b11dc502f6e8"}}