{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TKPPJXL4BAZTIVHRNVMMPWFE6B","short_pith_number":"pith:TKPPJXL4","schema_version":"1.0","canonical_sha256":"9a9ef4dd7c08333454f16d58c7d8a4f07158b6b1d6a664c71590df1d88c009fd","source":{"kind":"arxiv","id":"2303.08345","version":2},"attestation_state":"computed","paper":{"title":"Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Deli Zhao, Xiangteng He, Yiliang Lv, Yujun Shen, Yulin Pan, Yuxin Peng","submitted_at":"2023-03-15T03:54:43Z","abstract_excerpt":"Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (\\textit{e.g.}, in minutes), temporal grounding in long videos (\\textit{e.g.}, in hours) is still at its early stage. To address this challenge, a common practice is to employ a sliding window, yet can be inefficient and inflexible due to the limited number of frames within the window. In this work, we propose an end-to-end framework for fast temporal grounding, which is able to model an hours-long video with \\textbf{one-time} network execution. Our pipe"},"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":"2303.08345","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-15T03:54:43Z","cross_cats_sorted":[],"title_canon_sha256":"e3ac6edd9ea7481a8ec2346294153a691871ba132d499a54acee33e9adfadad4","abstract_canon_sha256":"afc9c6aaa0e3b981b74a98fe1d423aef17a8a8f861fd301947e1714db2538f34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:16.742847Z","signature_b64":"fwqXvKY+4f6jTAexrS3uya46hK3aQCTWHaFv6oDMy5I4MQnoKY+7EgBwfnCy/ROEjVZMJNVFuc8fldC8jn/wAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a9ef4dd7c08333454f16d58c7d8a4f07158b6b1d6a664c71590df1d88c009fd","last_reissued_at":"2026-07-05T07:46:16.742347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:16.742347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Deli Zhao, Xiangteng He, Yiliang Lv, Yujun Shen, Yulin Pan, Yuxin Peng","submitted_at":"2023-03-15T03:54:43Z","abstract_excerpt":"Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (\\textit{e.g.}, in minutes), temporal grounding in long videos (\\textit{e.g.}, in hours) is still at its early stage. To address this challenge, a common practice is to employ a sliding window, yet can be inefficient and inflexible due to the limited number of frames within the window. In this work, we propose an end-to-end framework for fast temporal grounding, which is able to model an hours-long video with \\textbf{one-time} network execution. Our pipe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08345","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/2303.08345/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":"2303.08345","created_at":"2026-07-05T07:46:16.742410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08345v2","created_at":"2026-07-05T07:46:16.742410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08345","created_at":"2026-07-05T07:46:16.742410+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKPPJXL4BAZT","created_at":"2026-07-05T07:46:16.742410+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKPPJXL4BAZTIVHR","created_at":"2026-07-05T07:46:16.742410+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKPPJXL4","created_at":"2026-07-05T07:46:16.742410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25276","citing_title":"OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B","json":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B.json","graph_json":"https://pith.science/api/pith-number/TKPPJXL4BAZTIVHRNVMMPWFE6B/graph.json","events_json":"https://pith.science/api/pith-number/TKPPJXL4BAZTIVHRNVMMPWFE6B/events.json","paper":"https://pith.science/paper/TKPPJXL4"},"agent_actions":{"view_html":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B","download_json":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B.json","view_paper":"https://pith.science/paper/TKPPJXL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08345&json=true","fetch_graph":"https://pith.science/api/pith-number/TKPPJXL4BAZTIVHRNVMMPWFE6B/graph.json","fetch_events":"https://pith.science/api/pith-number/TKPPJXL4BAZTIVHRNVMMPWFE6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B/action/storage_attestation","attest_author":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B/action/author_attestation","sign_citation":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B/action/citation_signature","submit_replication":"https://pith.science/pith/TKPPJXL4BAZTIVHRNVMMPWFE6B/action/replication_record"}},"created_at":"2026-07-05T07:46:16.742410+00:00","updated_at":"2026-07-05T07:46:16.742410+00:00"}