{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TY5U7XPGTGRLSFEWU6TZHK7SJF","short_pith_number":"pith:TY5U7XPG","canonical_record":{"source":{"id":"2403.19046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T22:50:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8ffc341938dd0f08b94efda8ec9f602d585bfcef1b4391f53dc3013d8d88980","abstract_canon_sha256":"f758cd960eaaa283369123344bfd17af227d86b88b7b6e87d16c743e48e6b6b1"},"schema_version":"1.0"},"canonical_sha256":"9e3b4fdde699a2b91496a7a793abf249590757b38a107744ddaa31b6ede5c3ca","source":{"kind":"arxiv","id":"2403.19046","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TY5U7XPGTGRLSFEWU6TZHK7SJF","target":"record","payload":{"canonical_record":{"source":{"id":"2403.19046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T22:50:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8ffc341938dd0f08b94efda8ec9f602d585bfcef1b4391f53dc3013d8d88980","abstract_canon_sha256":"f758cd960eaaa283369123344bfd17af227d86b88b7b6e87d16c743e48e6b6b1"},"schema_version":"1.0"},"canonical_sha256":"9e3b4fdde699a2b91496a7a793abf249590757b38a107744ddaa31b6ede5c3ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:43.442421Z","signature_b64":"gF4Qi808v/qcl2WSPzdM5+C/kGRIZjIscVRM2yNyYc0GD4YO5H8rp1XM5a3jx8+BuARedL/iN+t+ikuE5ZDqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e3b4fdde699a2b91496a7a793abf249590757b38a107744ddaa31b6ede5c3ca","last_reissued_at":"2026-07-05T08:01:43.441971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:43.441971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.19046","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:01:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"re6aV76iBo7uwZc0I8Vam1/lxuKxVHkZ5JpJbU0nvSNYl/PkoYmWBqzAfzdnWYN8hC4ZjoRFdrnDKtG4UJs5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:44:57.099829Z"},"content_sha256":"ee1602ffd6d79af3c5a0c55007cf161b45308ddad96811b144b2cb0d07efa4ca","schema_version":"1.0","event_id":"sha256:ee1602ffd6d79af3c5a0c55007cf161b45308ddad96811b144b2cb0d07efa4ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TY5U7XPGTGRLSFEWU6TZHK7SJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LITA: Language Instructed Temporal-Localization Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"De-An Huang, Hongxu Yin, Jan Kautz, Pavlo Molchanov, Shijia Liao, Subhashree Radhakrishnan, Zhiding Yu","submitted_at":"2024-03-27T22:50:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19046","kind":"arxiv","version":1},"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/2403.19046/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":"2026-07-05T08:01:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQo6tDLuXrkOlTZzBtcu3wT2K4U/A87wNkES3ui3j+z/LL4MS1GfeYwTNCr2pEYpfDV9EGGKDs1E0qIN0FSLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:44:57.100337Z"},"content_sha256":"fb6ea4f06b4ce74928bb216c2a73139ee2edc22221cc09928665338d7479c65d","schema_version":"1.0","event_id":"sha256:fb6ea4f06b4ce74928bb216c2a73139ee2edc22221cc09928665338d7479c65d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TY5U7XPGTGRLSFEWU6TZHK7SJF/bundle.json","state_url":"https://pith.science/pith/TY5U7XPGTGRLSFEWU6TZHK7SJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TY5U7XPGTGRLSFEWU6TZHK7SJF/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":"2026-08-15T17:44:57Z","links":{"resolver":"https://pith.science/pith/TY5U7XPGTGRLSFEWU6TZHK7SJF","bundle":"https://pith.science/pith/TY5U7XPGTGRLSFEWU6TZHK7SJF/bundle.json","state":"https://pith.science/pith/TY5U7XPGTGRLSFEWU6TZHK7SJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TY5U7XPGTGRLSFEWU6TZHK7SJF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZlyvsA5Qa8iPAAITDcTNdAUkd0+/SOb/Mz2Km/2bRgc2ufo56LdEXQXxwpZYicci1IcME6FiacO9OyW7R2EnAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:44:57.103677Z","bundle_sha256":"e51cc34c6d4022ac636641f36bee6d597743f06c9d22c4662301ae5f10cbad92"}}