{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JTBWSTAW4CW5L2UZ6FWHRNX4ET","short_pith_number":"pith:JTBWSTAW","schema_version":"1.0","canonical_sha256":"4cc3694c16e0add5ea99f16c78b6fc24d10d817cc613439327fd67c28c16a9d2","source":{"kind":"arxiv","id":"2312.00083","version":2},"attestation_state":"computed","paper":{"title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hyeran Byun, Pilhyeon Lee","submitted_at":"2023-11-30T07:16:11Z","abstract_excerpt":"Temporal sentence grounding aims to localize moments relevant to a language description. Recently, DETR-like approaches achieved notable progress by predicting the center and length of a target moment. However, they suffer from the issue of center misalignment raised by the inherent ambiguity of moment centers, leading to inaccurate predictions. To remedy this problem, we propose a novel boundary-oriented moment formulation. In our paradigm, the model no longer needs to find the precise center but instead suffices to predict any anchor point within the interval, from which the boundaries are d"},"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":"2312.00083","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T07:16:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a68fb9e4c86e10ebd3f9eeb4a0675d058f525ba1280e903f066c2121cd5cd165","abstract_canon_sha256":"165e4414c0318f8bd1ae41e63e1acbdf585ee8f459839227ff8b666ed519e9a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:23.734179Z","signature_b64":"lDTfYnbgNVCsceL5cjmWzerhGr8dndE5a+f7K08KCIKjM/M4YLLJOflO/hk4QC5phfGWignEWW0L750nTmECBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cc3694c16e0add5ea99f16c78b6fc24d10d817cc613439327fd67c28c16a9d2","last_reissued_at":"2026-07-05T08:45:23.733738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:23.733738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hyeran Byun, Pilhyeon Lee","submitted_at":"2023-11-30T07:16:11Z","abstract_excerpt":"Temporal sentence grounding aims to localize moments relevant to a language description. Recently, DETR-like approaches achieved notable progress by predicting the center and length of a target moment. However, they suffer from the issue of center misalignment raised by the inherent ambiguity of moment centers, leading to inaccurate predictions. To remedy this problem, we propose a novel boundary-oriented moment formulation. In our paradigm, the model no longer needs to find the precise center but instead suffices to predict any anchor point within the interval, from which the boundaries are d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00083","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/2312.00083/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":"2312.00083","created_at":"2026-07-05T08:45:23.733795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00083v2","created_at":"2026-07-05T08:45:23.733795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00083","created_at":"2026-07-05T08:45:23.733795+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTBWSTAW4CW5","created_at":"2026-07-05T08:45:23.733795+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTBWSTAW4CW5L2UZ","created_at":"2026-07-05T08:45:23.733795+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTBWSTAW","created_at":"2026-07-05T08:45:23.733795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00033","citing_title":"Moment Sampling in Video LLMs for Long-Form Video QA","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET","json":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET.json","graph_json":"https://pith.science/api/pith-number/JTBWSTAW4CW5L2UZ6FWHRNX4ET/graph.json","events_json":"https://pith.science/api/pith-number/JTBWSTAW4CW5L2UZ6FWHRNX4ET/events.json","paper":"https://pith.science/paper/JTBWSTAW"},"agent_actions":{"view_html":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET","download_json":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET.json","view_paper":"https://pith.science/paper/JTBWSTAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00083&json=true","fetch_graph":"https://pith.science/api/pith-number/JTBWSTAW4CW5L2UZ6FWHRNX4ET/graph.json","fetch_events":"https://pith.science/api/pith-number/JTBWSTAW4CW5L2UZ6FWHRNX4ET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET/action/storage_attestation","attest_author":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET/action/author_attestation","sign_citation":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET/action/citation_signature","submit_replication":"https://pith.science/pith/JTBWSTAW4CW5L2UZ6FWHRNX4ET/action/replication_record"}},"created_at":"2026-07-05T08:45:23.733795+00:00","updated_at":"2026-07-05T08:45:23.733795+00:00"}