{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5K7PEJMEP2IS35YJTLMVR2NWG6","short_pith_number":"pith:5K7PEJME","schema_version":"1.0","canonical_sha256":"eabef225847e912df7099ad958e9b637b362a0f86b4f0ed2d070942d8cf72102","source":{"kind":"arxiv","id":"2112.00475","version":1},"attestation_state":"computed","paper":{"title":"Weakly-Supervised Video Object Grounding via Causal Intervention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Junyu Gao, Wei Wang","submitted_at":"2021-12-01T13:13:03Z","abstract_excerpt":"We target at the task of weakly-supervised video object grounding (WSVOG), where only video-sentence annotations are available during model learning. It aims to localize objects described in the sentence to visual regions in the video, which is a fundamental capability needed in pattern analysis and machine learning. Despite the recent progress, existing methods all suffer from the severe problem of spurious association, which will harm the grounding performance. In this paper, we start from the definition of WSVOG and pinpoint the spurious association from two aspects: (1) the association its"},"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":"2112.00475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T13:13:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d3f9c4f7ddb0cba24c464282b20cdd299f2c3e36677a70b3aba62e78c365bd12","abstract_canon_sha256":"5b60f831bcf88911d48e0888818e7a3e96f41b08867596029da2a42fbe31d59a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:46.784227Z","signature_b64":"1iDl1X6NUV467tQ8xJQfZvnjGBH9C7zGeOvudOzF5nJpXltOZEO+UEDBvOKu1QsOVgSuX58hWJrKp88mxZTtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eabef225847e912df7099ad958e9b637b362a0f86b4f0ed2d070942d8cf72102","last_reissued_at":"2026-07-05T03:36:46.783741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:46.783741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly-Supervised Video Object Grounding via Causal Intervention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Junyu Gao, Wei Wang","submitted_at":"2021-12-01T13:13:03Z","abstract_excerpt":"We target at the task of weakly-supervised video object grounding (WSVOG), where only video-sentence annotations are available during model learning. It aims to localize objects described in the sentence to visual regions in the video, which is a fundamental capability needed in pattern analysis and machine learning. Despite the recent progress, existing methods all suffer from the severe problem of spurious association, which will harm the grounding performance. In this paper, we start from the definition of WSVOG and pinpoint the spurious association from two aspects: (1) the association its"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00475","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/2112.00475/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":"2112.00475","created_at":"2026-07-05T03:36:46.783800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00475v1","created_at":"2026-07-05T03:36:46.783800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00475","created_at":"2026-07-05T03:36:46.783800+00:00"},{"alias_kind":"pith_short_12","alias_value":"5K7PEJMEP2IS","created_at":"2026-07-05T03:36:46.783800+00:00"},{"alias_kind":"pith_short_16","alias_value":"5K7PEJMEP2IS35YJ","created_at":"2026-07-05T03:36:46.783800+00:00"},{"alias_kind":"pith_short_8","alias_value":"5K7PEJME","created_at":"2026-07-05T03:36:46.783800+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/5K7PEJMEP2IS35YJTLMVR2NWG6","json":"https://pith.science/pith/5K7PEJMEP2IS35YJTLMVR2NWG6.json","graph_json":"https://pith.science/api/pith-number/5K7PEJMEP2IS35YJTLMVR2NWG6/graph.json","events_json":"https://pith.science/api/pith-number/5K7PEJMEP2IS35YJTLMVR2NWG6/events.json","paper":"https://pith.science/paper/5K7PEJME"},"agent_actions":{"view_html":"https://pith.science/pith/5K7PEJMEP2IS35YJTLMVR2NWG6","download_json":"https://pith.science/pith/5K7PEJMEP2IS35YJTLMVR2NWG6.json","view_paper":"https://pith.science/paper/5K7PEJME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00475&json=true","fetch_graph":"https://pith.science/api/pith-number/5K7PEJMEP2IS35YJTLMVR2NWG6/graph.json","fetch_events":"https://pith.science/api/pith-number/5K7PEJMEP2IS35YJTLMVR2NWG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5K7PEJMEP2IS35YJTLMVR2NWG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5K7PEJMEP2IS35YJTLMVR2NWG6/action/storage_attestation","attest_author":"https://pith.science/pith/5K7PEJMEP2IS35YJTLMVR2NWG6/action/author_attestation","sign_citation":"https://pith.science/pith/5K7PEJMEP2IS35YJTLMVR2NWG6/action/citation_signature","submit_replication":"https://pith.science/pith/5K7PEJMEP2IS35YJTLMVR2NWG6/action/replication_record"}},"created_at":"2026-07-05T03:36:46.783800+00:00","updated_at":"2026-07-05T03:36:46.783800+00:00"}