{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TY5U7XPGTGRLSFEWU6TZHK7SJF","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":"f758cd960eaaa283369123344bfd17af227d86b88b7b6e87d16c743e48e6b6b1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T22:50:48Z","title_canon_sha256":"d8ffc341938dd0f08b94efda8ec9f602d585bfcef1b4391f53dc3013d8d88980"},"schema_version":"1.0","source":{"id":"2403.19046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19046","created_at":"2026-07-05T08:01:43Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19046v1","created_at":"2026-07-05T08:01:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19046","created_at":"2026-07-05T08:01:43Z"},{"alias_kind":"pith_short_12","alias_value":"TY5U7XPGTGRL","created_at":"2026-07-05T08:01:43Z"},{"alias_kind":"pith_short_16","alias_value":"TY5U7XPGTGRLSFEW","created_at":"2026-07-05T08:01:43Z"},{"alias_kind":"pith_short_8","alias_value":"TY5U7XPG","created_at":"2026-07-05T08:01:43Z"}],"graph_snapshots":[{"event_id":"sha256:fb6ea4f06b4ce74928bb216c2a73139ee2edc22221cc09928665338d7479c65d","target":"graph","created_at":"2026-07-05T08:01:43Z","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/2403.19046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been tremendous progress in multimodal Large Language Models (LLMs). Recent works have extended these models to video input with promising instruction following capabilities. However, an important missing piece is temporal localization. These models cannot accurately answer the \"When?\" questions. We identify three key aspects that limit their temporal localization capabilities: (i) time representation, (ii) architecture, and (iii) data. We address these shortcomings by proposing Language Instructed Temporal-Localization Assistant (LITA) with the following features: (1) We introduce t","authors_text":"De-An Huang, Hongxu Yin, Jan Kautz, Pavlo Molchanov, Shijia Liao, Subhashree Radhakrishnan, Zhiding Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T22:50:48Z","title":"LITA: Language Instructed Temporal-Localization Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19046","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:ee1602ffd6d79af3c5a0c55007cf161b45308ddad96811b144b2cb0d07efa4ca","target":"record","created_at":"2026-07-05T08:01:43Z","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":"f758cd960eaaa283369123344bfd17af227d86b88b7b6e87d16c743e48e6b6b1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T22:50:48Z","title_canon_sha256":"d8ffc341938dd0f08b94efda8ec9f602d585bfcef1b4391f53dc3013d8d88980"},"schema_version":"1.0","source":{"id":"2403.19046","kind":"arxiv","version":1}},"canonical_sha256":"9e3b4fdde699a2b91496a7a793abf249590757b38a107744ddaa31b6ede5c3ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e3b4fdde699a2b91496a7a793abf249590757b38a107744ddaa31b6ede5c3ca","first_computed_at":"2026-07-05T08:01:43.441971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:43.441971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gF4Qi808v/qcl2WSPzdM5+C/kGRIZjIscVRM2yNyYc0GD4YO5H8rp1XM5a3jx8+BuARedL/iN+t+ikuE5ZDqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:43.442421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee1602ffd6d79af3c5a0c55007cf161b45308ddad96811b144b2cb0d07efa4ca","sha256:fb6ea4f06b4ce74928bb216c2a73139ee2edc22221cc09928665338d7479c65d"],"state_sha256":"88e55bd86bf44ee973deee0809ea1dee9eff86ecbe3dafafac0b2152b879afdc"}