{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VFAR4VIHMFGGCBMYLH3CSD5GWX","short_pith_number":"pith:VFAR4VIH","schema_version":"1.0","canonical_sha256":"a9411e5507614c61059859f6290fa6b5e4d497c97f8132bad0cf3c66b1d324d4","source":{"kind":"arxiv","id":"2302.13372","version":2},"attestation_state":"computed","paper":{"title":"Localizing Moments in Long Video Via Multimodal Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alberto Mario Ceballos-Arroyo, Bernard Ghanem, Fabian Caba Heilbron, Mattia Soldan, Wayner Barrios","submitted_at":"2023-02-26T18:19:24Z","abstract_excerpt":"The recent introduction of the large-scale, long-form MAD and Ego4D datasets has enabled researchers to investigate the performance of current state-of-the-art methods for video grounding in the long-form setup, with interesting findings: current grounding methods alone fail at tackling this challenging task and setup due to their inability to process long video sequences. In this paper, we propose a method for improving the performance of natural language grounding in long videos by identifying and pruning out non-describable windows. We design a guided grounding framework consisting of a Gui"},"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":"2302.13372","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-26T18:19:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e54c8a254d4c92bc9bdcb5520dcf840225a0e7978c74f9ed2326599d7310c8ef","abstract_canon_sha256":"93c3ecfb1189acf1899dc8a363568b197d18cc3292c3832694688a4b81274afd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:59.241794Z","signature_b64":"1Z5yWn7Q5bfnUq4FZQdYDAoAInWKL3UIW5u5gc8fiMNbd4HGE0VtVOTye0kGjiDw6bB3egYMFTbPmBPQWWT5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9411e5507614c61059859f6290fa6b5e4d497c97f8132bad0cf3c66b1d324d4","last_reissued_at":"2026-07-05T07:00:59.241355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:59.241355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Localizing Moments in Long Video Via Multimodal Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alberto Mario Ceballos-Arroyo, Bernard Ghanem, Fabian Caba Heilbron, Mattia Soldan, Wayner Barrios","submitted_at":"2023-02-26T18:19:24Z","abstract_excerpt":"The recent introduction of the large-scale, long-form MAD and Ego4D datasets has enabled researchers to investigate the performance of current state-of-the-art methods for video grounding in the long-form setup, with interesting findings: current grounding methods alone fail at tackling this challenging task and setup due to their inability to process long video sequences. In this paper, we propose a method for improving the performance of natural language grounding in long videos by identifying and pruning out non-describable windows. We design a guided grounding framework consisting of a Gui"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13372","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/2302.13372/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":"2302.13372","created_at":"2026-07-05T07:00:59.241415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13372v2","created_at":"2026-07-05T07:00:59.241415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13372","created_at":"2026-07-05T07:00:59.241415+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFAR4VIHMFGG","created_at":"2026-07-05T07:00:59.241415+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFAR4VIHMFGGCBMY","created_at":"2026-07-05T07:00:59.241415+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFAR4VIH","created_at":"2026-07-05T07:00:59.241415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16376","citing_title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX","json":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX.json","graph_json":"https://pith.science/api/pith-number/VFAR4VIHMFGGCBMYLH3CSD5GWX/graph.json","events_json":"https://pith.science/api/pith-number/VFAR4VIHMFGGCBMYLH3CSD5GWX/events.json","paper":"https://pith.science/paper/VFAR4VIH"},"agent_actions":{"view_html":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX","download_json":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX.json","view_paper":"https://pith.science/paper/VFAR4VIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13372&json=true","fetch_graph":"https://pith.science/api/pith-number/VFAR4VIHMFGGCBMYLH3CSD5GWX/graph.json","fetch_events":"https://pith.science/api/pith-number/VFAR4VIHMFGGCBMYLH3CSD5GWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX/action/storage_attestation","attest_author":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX/action/author_attestation","sign_citation":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX/action/citation_signature","submit_replication":"https://pith.science/pith/VFAR4VIHMFGGCBMYLH3CSD5GWX/action/replication_record"}},"created_at":"2026-07-05T07:00:59.241415+00:00","updated_at":"2026-07-05T07:00:59.241415+00:00"}