{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JE3X2ME3USWCDSAJIVP4EZ4QDB","short_pith_number":"pith:JE3X2ME3","schema_version":"1.0","canonical_sha256":"49377d309ba4ac21c809455fc2679018416b450c415269d0b6448e4dc63aca42","source":{"kind":"arxiv","id":"2503.23181","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daeho Um, Sunoh Kim","submitted_at":"2025-03-29T18:33:58Z","abstract_excerpt":"Weakly supervised video grounding aims to localize temporal boundaries relevant to a given query without explicit ground-truth temporal boundaries. While existing methods primarily use Gaussian-based proposals, they overlook the importance of (1) boundary prediction and (2) top-1 prediction selection during inference. In their boundary prediction, boundaries are simply set at half a standard deviation away from a Gaussian mean on both sides, which may not accurately capture the optimal boundaries. In the top-1 prediction process, these existing methods rely heavily on intersections with other "},"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":"2503.23181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-29T18:33:58Z","cross_cats_sorted":[],"title_canon_sha256":"949848c3ab843f7a7d09e20ff97f80117f724b6dfc3b513c7b14052ceb812953","abstract_canon_sha256":"19aa80bd972636659722ff154521459f4d6705b394fc3776d1468907e2602160"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:31.903134Z","signature_b64":"3kMxXSbNuNqc7lOOYCS7pJf0VkjF7nvTY82hk+f1EVFJ4JePsutCT1kYOYKNk9R3/qrqmdWbMOc3hlWPmr4rBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49377d309ba4ac21c809455fc2679018416b450c415269d0b6448e4dc63aca42","last_reissued_at":"2026-07-05T10:41:31.902665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:31.902665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daeho Um, Sunoh Kim","submitted_at":"2025-03-29T18:33:58Z","abstract_excerpt":"Weakly supervised video grounding aims to localize temporal boundaries relevant to a given query without explicit ground-truth temporal boundaries. While existing methods primarily use Gaussian-based proposals, they overlook the importance of (1) boundary prediction and (2) top-1 prediction selection during inference. In their boundary prediction, boundaries are simply set at half a standard deviation away from a Gaussian mean on both sides, which may not accurately capture the optimal boundaries. In the top-1 prediction process, these existing methods rely heavily on intersections with other "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23181","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/2503.23181/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":"2503.23181","created_at":"2026-07-05T10:41:31.902723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23181v1","created_at":"2026-07-05T10:41:31.902723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23181","created_at":"2026-07-05T10:41:31.902723+00:00"},{"alias_kind":"pith_short_12","alias_value":"JE3X2ME3USWC","created_at":"2026-07-05T10:41:31.902723+00:00"},{"alias_kind":"pith_short_16","alias_value":"JE3X2ME3USWCDSAJ","created_at":"2026-07-05T10:41:31.902723+00:00"},{"alias_kind":"pith_short_8","alias_value":"JE3X2ME3","created_at":"2026-07-05T10:41:31.902723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB","json":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB.json","graph_json":"https://pith.science/api/pith-number/JE3X2ME3USWCDSAJIVP4EZ4QDB/graph.json","events_json":"https://pith.science/api/pith-number/JE3X2ME3USWCDSAJIVP4EZ4QDB/events.json","paper":"https://pith.science/paper/JE3X2ME3"},"agent_actions":{"view_html":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB","download_json":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB.json","view_paper":"https://pith.science/paper/JE3X2ME3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23181&json=true","fetch_graph":"https://pith.science/api/pith-number/JE3X2ME3USWCDSAJIVP4EZ4QDB/graph.json","fetch_events":"https://pith.science/api/pith-number/JE3X2ME3USWCDSAJIVP4EZ4QDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB/action/storage_attestation","attest_author":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB/action/author_attestation","sign_citation":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB/action/citation_signature","submit_replication":"https://pith.science/pith/JE3X2ME3USWCDSAJIVP4EZ4QDB/action/replication_record"}},"created_at":"2026-07-05T10:41:31.902723+00:00","updated_at":"2026-07-05T10:41:31.902723+00:00"}