{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OB2YA6VL2AK363O3NEYCPBV7OK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9ccbb55c1c3d0c2555d589ba691927fb7e0c07257c72f06ec7dbaa8e76485a7d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T05:40:54Z","title_canon_sha256":"7d7793c02c64abd42b51c2afa53f80c7cebcbd2702d018bc15191d98a90efc36"},"schema_version":"1.0","source":{"id":"2506.03589","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03589","created_at":"2026-07-05T11:32:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03589v3","created_at":"2026-07-05T11:32:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03589","created_at":"2026-07-05T11:32:29Z"},{"alias_kind":"pith_short_12","alias_value":"OB2YA6VL2AK3","created_at":"2026-07-05T11:32:29Z"},{"alias_kind":"pith_short_16","alias_value":"OB2YA6VL2AK363O3","created_at":"2026-07-05T11:32:29Z"},{"alias_kind":"pith_short_8","alias_value":"OB2YA6VL","created_at":"2026-07-05T11:32:29Z"}],"graph_snapshots":[{"event_id":"sha256:b9712e6eda4142803b4a5d342466d2e20d675a613e427f7133caede552ab90dc","target":"graph","created_at":"2026-07-05T11:32:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.03589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-video retrieval (TVR) systems often suffer from visual-linguistic biases present in datasets, which cause pre-trained vision-language models to overlook key details. To address this, we propose BiMa, a novel framework designed to mitigate biases in both visual and textual representations. Our approach begins by generating scene elements that characterize each video by identifying relevant entities/objects and activities. For visual debiasing, we integrate these scene elements into the video embeddings, enhancing them to emphasize fine-grained and salient details. For textual debiasing, we","authors_text":"Anh Nguyen, Huy Le, Ngan Le, Nhat Chung, Tung Kieu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T05:40:54Z","title":"BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03589","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f4c08865d9a472acee35cd7c9b770cc258561c4c63b29ca97f3d167a44f9382a","target":"record","created_at":"2026-07-05T11:32:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9ccbb55c1c3d0c2555d589ba691927fb7e0c07257c72f06ec7dbaa8e76485a7d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T05:40:54Z","title_canon_sha256":"7d7793c02c64abd42b51c2afa53f80c7cebcbd2702d018bc15191d98a90efc36"},"schema_version":"1.0","source":{"id":"2506.03589","kind":"arxiv","version":3}},"canonical_sha256":"7075807aabd015bf6ddb69302786bf72bfaa2a62d36ce1c8b94fae551545b1e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7075807aabd015bf6ddb69302786bf72bfaa2a62d36ce1c8b94fae551545b1e0","first_computed_at":"2026-07-05T11:32:29.996710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:29.996710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DazENtPElUH5xrZayUjbKB8imEsbB5K+OekhDN9ceodCSy4pLBPbFSOMoosPWy3S5ARTyzd1FPTt+QGTEo3ABw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:29.997186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03589","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4c08865d9a472acee35cd7c9b770cc258561c4c63b29ca97f3d167a44f9382a","sha256:b9712e6eda4142803b4a5d342466d2e20d675a613e427f7133caede552ab90dc"],"state_sha256":"80d8d8ded3662e8bdb21c4f6eca3145051851687f4fc874dab13264ea5567b3e"}