{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DAUTZFKXSR6H3TFODA7CVENWPT","short_pith_number":"pith:DAUTZFKX","schema_version":"1.0","canonical_sha256":"18293c9557947c7dccae183e2a91b67ce5cd619ddca9894dd57b08c38466f99e","source":{"kind":"arxiv","id":"2508.10922","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Jianlong Wu, Liqiang Nie, Meng Liu, Wei Liu, Ye Liu, Zhouchen Lin","submitted_at":"2025-08-07T08:52:11Z","abstract_excerpt":"The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning abilities, VTG approaches based on MLLMs (VTG-MLLMs) are gradually surpassing traditional fine-tuned methods. They not only achieve competitive performance but also excel in generalization across zero-shot, multi-task, and multi-domain settings. Despite extensive surveys on general video-language understanding, comprehensive reviews specifically addressing VTG-MLLM"},"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":"2508.10922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T08:52:11Z","cross_cats_sorted":[],"title_canon_sha256":"39dd5c1613340659b3a4a23648ab7de2d6f46d9292140d9c430a07d7540a4910","abstract_canon_sha256":"209594104abbf9f0efbeac6f30008983178737048ae3345c68c43740849079ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:14.889102Z","signature_b64":"Iyug08TK5tl1I2VkNP2DvwLx3+YJISIBjb6yNKDXoDzJaMszbFDPZ5M3z9IZtweLXAvALeYdNUZMv1BJgQbrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18293c9557947c7dccae183e2a91b67ce5cd619ddca9894dd57b08c38466f99e","last_reissued_at":"2026-07-05T11:54:14.888445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:14.888445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Jianlong Wu, Liqiang Nie, Meng Liu, Wei Liu, Ye Liu, Zhouchen Lin","submitted_at":"2025-08-07T08:52:11Z","abstract_excerpt":"The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning abilities, VTG approaches based on MLLMs (VTG-MLLMs) are gradually surpassing traditional fine-tuned methods. They not only achieve competitive performance but also excel in generalization across zero-shot, multi-task, and multi-domain settings. Despite extensive surveys on general video-language understanding, comprehensive reviews specifically addressing VTG-MLLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10922","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/2508.10922/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":"2508.10922","created_at":"2026-07-05T11:54:14.888524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10922v1","created_at":"2026-07-05T11:54:14.888524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10922","created_at":"2026-07-05T11:54:14.888524+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAUTZFKXSR6H","created_at":"2026-07-05T11:54:14.888524+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAUTZFKXSR6H3TFO","created_at":"2026-07-05T11:54:14.888524+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAUTZFKX","created_at":"2026-07-05T11:54:14.888524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19706","citing_title":"NEST: Narrative Event Structures in Time for Long Video Understanding","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12300","citing_title":"Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT","json":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT.json","graph_json":"https://pith.science/api/pith-number/DAUTZFKXSR6H3TFODA7CVENWPT/graph.json","events_json":"https://pith.science/api/pith-number/DAUTZFKXSR6H3TFODA7CVENWPT/events.json","paper":"https://pith.science/paper/DAUTZFKX"},"agent_actions":{"view_html":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT","download_json":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT.json","view_paper":"https://pith.science/paper/DAUTZFKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10922&json=true","fetch_graph":"https://pith.science/api/pith-number/DAUTZFKXSR6H3TFODA7CVENWPT/graph.json","fetch_events":"https://pith.science/api/pith-number/DAUTZFKXSR6H3TFODA7CVENWPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT/action/storage_attestation","attest_author":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT/action/author_attestation","sign_citation":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT/action/citation_signature","submit_replication":"https://pith.science/pith/DAUTZFKXSR6H3TFODA7CVENWPT/action/replication_record"}},"created_at":"2026-07-05T11:54:14.888524+00:00","updated_at":"2026-07-05T11:54:14.888524+00:00"}