{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:36ID4GW775WIR5M5HZWWPFSCQ3","short_pith_number":"pith:36ID4GW7","schema_version":"1.0","canonical_sha256":"df903e1adfff6c88f59d3e6d67964286fd3fa7c40882fe1c18014b585a0ac512","source":{"kind":"arxiv","id":"2402.16050","version":2},"attestation_state":"computed","paper":{"title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Jianxin Liang, Pengfei Wu, Yang Liu, Yueqian Wang, Yuxuan Wang, Zilong Zheng","submitted_at":"2024-02-25T10:27:46Z","abstract_excerpt":"Despite progress in multimodal large language models (MLLMs), the challenge of interpreting long-form videos in response to linguistic queries persists, largely due to the inefficiency in temporal grounding and limited pre-trained context window size. In this work, we introduce Temporal Grounding Bridge (TGB), a novel framework that bootstraps MLLMs with advanced temporal grounding capabilities and broadens their contextual scope. Our framework significantly enhances the temporal capabilities of current MLLMs through three key innovations: an efficient multi-span temporal grounding algorithm a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.16050","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-25T10:27:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e1ba933d5933e3cfdaf92fd45158140e6955b1daf92b7f795512439c7d3c1d69","abstract_canon_sha256":"6785fdcf22d738531335d4ddd7f606e2210f6954048780ab8b73476b004625e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:08.764592Z","signature_b64":"FgZzMbZsKjoOJs2lvFN8gqZq3q1KTwm6KfuY4wuGCDYngRietHiJhzmTXHf0qW1a1IfCKx5zTh6KmVi40FZfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df903e1adfff6c88f59d3e6d67964286fd3fa7c40882fe1c18014b585a0ac512","last_reissued_at":"2026-07-05T09:15:08.764146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:08.764146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Jianxin Liang, Pengfei Wu, Yang Liu, Yueqian Wang, Yuxuan Wang, Zilong Zheng","submitted_at":"2024-02-25T10:27:46Z","abstract_excerpt":"Despite progress in multimodal large language models (MLLMs), the challenge of interpreting long-form videos in response to linguistic queries persists, largely due to the inefficiency in temporal grounding and limited pre-trained context window size. In this work, we introduce Temporal Grounding Bridge (TGB), a novel framework that bootstraps MLLMs with advanced temporal grounding capabilities and broadens their contextual scope. Our framework significantly enhances the temporal capabilities of current MLLMs through three key innovations: an efficient multi-span temporal grounding algorithm a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16050","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/2402.16050/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.16050","created_at":"2026-07-05T09:15:08.764201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16050v2","created_at":"2026-07-05T09:15:08.764201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16050","created_at":"2026-07-05T09:15:08.764201+00:00"},{"alias_kind":"pith_short_12","alias_value":"36ID4GW775WI","created_at":"2026-07-05T09:15:08.764201+00:00"},{"alias_kind":"pith_short_16","alias_value":"36ID4GW775WIR5M5","created_at":"2026-07-05T09:15:08.764201+00:00"},{"alias_kind":"pith_short_8","alias_value":"36ID4GW7","created_at":"2026-07-05T09:15:08.764201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.03963","citing_title":"TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3","json":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3.json","graph_json":"https://pith.science/api/pith-number/36ID4GW775WIR5M5HZWWPFSCQ3/graph.json","events_json":"https://pith.science/api/pith-number/36ID4GW775WIR5M5HZWWPFSCQ3/events.json","paper":"https://pith.science/paper/36ID4GW7"},"agent_actions":{"view_html":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3","download_json":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3.json","view_paper":"https://pith.science/paper/36ID4GW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16050&json=true","fetch_graph":"https://pith.science/api/pith-number/36ID4GW775WIR5M5HZWWPFSCQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/36ID4GW775WIR5M5HZWWPFSCQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3/action/storage_attestation","attest_author":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3/action/author_attestation","sign_citation":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3/action/citation_signature","submit_replication":"https://pith.science/pith/36ID4GW775WIR5M5HZWWPFSCQ3/action/replication_record"}},"created_at":"2026-07-05T09:15:08.764201+00:00","updated_at":"2026-07-05T09:15:08.764201+00:00"}