{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OB2YA6VL2AK363O3NEYCPBV7OK","short_pith_number":"pith:OB2YA6VL","canonical_record":{"source":{"id":"2506.03589","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T05:40:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7d7793c02c64abd42b51c2afa53f80c7cebcbd2702d018bc15191d98a90efc36","abstract_canon_sha256":"9ccbb55c1c3d0c2555d589ba691927fb7e0c07257c72f06ec7dbaa8e76485a7d"},"schema_version":"1.0"},"canonical_sha256":"7075807aabd015bf6ddb69302786bf72bfaa2a62d36ce1c8b94fae551545b1e0","source":{"kind":"arxiv","id":"2506.03589","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OB2YA6VL2AK363O3NEYCPBV7OK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03589","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T05:40:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7d7793c02c64abd42b51c2afa53f80c7cebcbd2702d018bc15191d98a90efc36","abstract_canon_sha256":"9ccbb55c1c3d0c2555d589ba691927fb7e0c07257c72f06ec7dbaa8e76485a7d"},"schema_version":"1.0"},"canonical_sha256":"7075807aabd015bf6ddb69302786bf72bfaa2a62d36ce1c8b94fae551545b1e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:29.997186Z","signature_b64":"DazENtPElUH5xrZayUjbKB8imEsbB5K+OekhDN9ceodCSy4pLBPbFSOMoosPWy3S5ARTyzd1FPTt+QGTEo3ABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7075807aabd015bf6ddb69302786bf72bfaa2a62d36ce1c8b94fae551545b1e0","last_reissued_at":"2026-07-05T11:32:29.996710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:29.996710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03589","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Up5pF+kFTb8Ms3C+Ap69ZlBrvh7y4EZFf5Av/NtalsSLy2j74XJx8q4ZfUGR2hUxOHrjxEjr1DWOIRz1ICGCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:31:55.284784Z"},"content_sha256":"f4c08865d9a472acee35cd7c9b770cc258561c4c63b29ca97f3d167a44f9382a","schema_version":"1.0","event_id":"sha256:f4c08865d9a472acee35cd7c9b770cc258561c4c63b29ca97f3d167a44f9382a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OB2YA6VL2AK363O3NEYCPBV7OK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Huy Le, Ngan Le, Nhat Chung, Tung Kieu","submitted_at":"2025-06-04T05:40:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03589","kind":"arxiv","version":3},"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/2506.03589/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XT2BBAexRsybia6nu22K4d9Fb2jd5f/VY+RkcZ4bLa7A7SEvBjpvdV5T5imDPAXRJI259vpUK24sOLgPM8NlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:31:55.285280Z"},"content_sha256":"b9712e6eda4142803b4a5d342466d2e20d675a613e427f7133caede552ab90dc","schema_version":"1.0","event_id":"sha256:b9712e6eda4142803b4a5d342466d2e20d675a613e427f7133caede552ab90dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OB2YA6VL2AK363O3NEYCPBV7OK/bundle.json","state_url":"https://pith.science/pith/OB2YA6VL2AK363O3NEYCPBV7OK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OB2YA6VL2AK363O3NEYCPBV7OK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T02:31:55Z","links":{"resolver":"https://pith.science/pith/OB2YA6VL2AK363O3NEYCPBV7OK","bundle":"https://pith.science/pith/OB2YA6VL2AK363O3NEYCPBV7OK/bundle.json","state":"https://pith.science/pith/OB2YA6VL2AK363O3NEYCPBV7OK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OB2YA6VL2AK363O3NEYCPBV7OK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8ckA0svCskxNVoUECLzeCBauATNr/6yMLQj+jJ2m0YjxrZ6UWnAkdA7+EyS/ScLTz4mrSCMdUuOBI8PvABfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:31:55.289281Z","bundle_sha256":"fd37ebdc87709faf125338410324055e4def27aceffd759f4bae216acb2c0139"}}