{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZIE4DWVZYM73HEVOVKWAFPV6OR","short_pith_number":"pith:ZIE4DWVZ","schema_version":"1.0","canonical_sha256":"ca09c1dab9c33fb392aeaaac02bebe7453af6f020bdff2e822d0664e84d277ca","source":{"kind":"arxiv","id":"2405.13382","version":3},"attestation_state":"computed","paper":{"title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dianbo Sui, Dingxin Cheng, Jingyu Liu, Kevin Zhao, Mingda Li, Qingbin Liu, Xiaoying Tang, Xi Chen, Yongxin Guo","submitted_at":"2024-05-22T06:31:42Z","abstract_excerpt":"Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models, Video Large Language Models (video LLMs) can handle multiple tasks concurrently in a zero-shot manner. Consequently, exploring the application of video LLMs for VTG tasks has become a burgeoning research area. However, despite considerable advancements in video content understanding, video LLMs often struggle to accurately pinpoint timestamps within videos, "},"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":"2405.13382","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T06:31:42Z","cross_cats_sorted":[],"title_canon_sha256":"6690d559ce2b7744354f090179e954c39914b9574736243977b94ccb7c839b4b","abstract_canon_sha256":"431e19a28e8acb1e28fffb58dd2d5c1ceea4fa45a6fe7d6b641aa7617084a752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:16.955930Z","signature_b64":"0GJWX/t3aFy6+JDxE5ewbLkHlJ/sOc2JIANBjRk7v5yO1qb9yC3M449yNNFuDC8/M2ZV3xK8axp9g1iWUCqXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca09c1dab9c33fb392aeaaac02bebe7453af6f020bdff2e822d0664e84d277ca","last_reissued_at":"2026-07-05T10:08:16.955509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:16.955509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dianbo Sui, Dingxin Cheng, Jingyu Liu, Kevin Zhao, Mingda Li, Qingbin Liu, Xiaoying Tang, Xi Chen, Yongxin Guo","submitted_at":"2024-05-22T06:31:42Z","abstract_excerpt":"Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models, Video Large Language Models (video LLMs) can handle multiple tasks concurrently in a zero-shot manner. Consequently, exploring the application of video LLMs for VTG tasks has become a burgeoning research area. However, despite considerable advancements in video content understanding, video LLMs often struggle to accurately pinpoint timestamps within videos, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13382","kind":"arxiv","version":3},"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/2405.13382/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":"2405.13382","created_at":"2026-07-05T10:08:16.955568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13382v3","created_at":"2026-07-05T10:08:16.955568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13382","created_at":"2026-07-05T10:08:16.955568+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIE4DWVZYM73","created_at":"2026-07-05T10:08:16.955568+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIE4DWVZYM73HEVO","created_at":"2026-07-05T10:08:16.955568+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIE4DWVZ","created_at":"2026-07-05T10:08:16.955568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25886","citing_title":"MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13803","citing_title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02860","citing_title":"A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25886","citing_title":"MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR","json":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR.json","graph_json":"https://pith.science/api/pith-number/ZIE4DWVZYM73HEVOVKWAFPV6OR/graph.json","events_json":"https://pith.science/api/pith-number/ZIE4DWVZYM73HEVOVKWAFPV6OR/events.json","paper":"https://pith.science/paper/ZIE4DWVZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR","download_json":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR.json","view_paper":"https://pith.science/paper/ZIE4DWVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13382&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIE4DWVZYM73HEVOVKWAFPV6OR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIE4DWVZYM73HEVOVKWAFPV6OR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR/action/storage_attestation","attest_author":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR/action/author_attestation","sign_citation":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR/action/citation_signature","submit_replication":"https://pith.science/pith/ZIE4DWVZYM73HEVOVKWAFPV6OR/action/replication_record"}},"created_at":"2026-07-05T10:08:16.955568+00:00","updated_at":"2026-07-05T10:08:16.955568+00:00"}