{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QEC4EI6C7ZIWRVXZYZ5ETDIQSL","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":"f699ced6ba63c07be926ea585345fcbece951f24ed97b0af4ed7d2da5f91dcde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T01:40:25Z","title_canon_sha256":"7bc4b2e1d022e42dcbd7eee8f68f16c5353489599a3d1c0ccca599eab7ee2b10"},"schema_version":"1.0","source":{"id":"2505.12605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12605","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12605v1","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12605","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"QEC4EI6C7ZIW","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"QEC4EI6C7ZIWRVXZ","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"QEC4EI6C","created_at":"2026-07-05T11:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:6deee13cdca68b387aaa0e2407ffe556be884db21329d175c671040e9509d8b1","target":"graph","created_at":"2026-07-05T11:05:06Z","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/2505.12605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have witnessed outstanding advances of large vision-language models (LVLMs). In order to tackle video understanding, most of them depend upon their implicit temporal understanding capacity. As such, they have not deciphered important components that contribute to temporal understanding ability, which might limit the potential of these LVLMs for video understanding. In this work, we conduct a thorough empirical study to demystify crucial components that influence the temporal understanding of LVLMs. Our empirical study reveals that significant impacts are centered around the interm","authors_text":"Cong-Duy Nguyen, Luu Anh Tuan, See-kiong Ng, Thong Nguyen, Xu Lin, Zhiyuan Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T01:40:25Z","title":"Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12605","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:d856d6f7c6716b47f3b259d4d6ff6817b2d2a1c94f4345c6f696e6488ad707bd","target":"record","created_at":"2026-07-05T11:05:06Z","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":"f699ced6ba63c07be926ea585345fcbece951f24ed97b0af4ed7d2da5f91dcde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T01:40:25Z","title_canon_sha256":"7bc4b2e1d022e42dcbd7eee8f68f16c5353489599a3d1c0ccca599eab7ee2b10"},"schema_version":"1.0","source":{"id":"2505.12605","kind":"arxiv","version":1}},"canonical_sha256":"8105c223c2fe5168d6f9c67a498d1092da7fc943b04f6bc019b8ef0569f5ae96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8105c223c2fe5168d6f9c67a498d1092da7fc943b04f6bc019b8ef0569f5ae96","first_computed_at":"2026-07-05T11:05:06.797286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:06.797286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZVox1K9M0FSVdzqbrp5W/ziNwMfBpHf0cm4kamkVjNd+5u0D3NN/YTXZNMC3Um+CI0uKzDjwOaLAJayQug4WAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:06.797808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d856d6f7c6716b47f3b259d4d6ff6817b2d2a1c94f4345c6f696e6488ad707bd","sha256:6deee13cdca68b387aaa0e2407ffe556be884db21329d175c671040e9509d8b1"],"state_sha256":"ae59cb9c9b87917e153e0d7c71897bfc2d913fbe4ad65ca96f9a193c8ab2b315"}