{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AAITS4U4NLAZNPPILC6K6BUTRQ","short_pith_number":"pith:AAITS4U4","schema_version":"1.0","canonical_sha256":"001139729c6ac196bde858bcaf06938c2eb0aa1eee8fb3166df1baeb87c102d9","source":{"kind":"arxiv","id":"2501.11469","version":1},"attestation_state":"computed","paper":{"title":"MASS: Overcoming Language Bias in Image-Text Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiwan Chung, Sangkyu Lee, Seungwon Lim, Youngjae Yu","submitted_at":"2025-01-20T12:56:28Z","abstract_excerpt":"Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language priors and neglect to adequately consider the visual content. We thus present Multimodal ASsociation Score (MASS), a framework that reduces the reliance on language priors for better visual accuracy in image-text matching problems. It can be seamlessly incorporated into existing visual-language models without necessitating additional training. Our experiments"},"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":"2501.11469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T12:56:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d96e4fce819fa387343a541199ed88224fc01a44d79a351b59d5d1f94d991402","abstract_canon_sha256":"c008edde4802ea1f2d6904b80cb4bc373d3c09f837e9b8c862105f7e17b2e3c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:09.002683Z","signature_b64":"JQCE84UgcOPsifGTNayRm/kwGgAbeSTrRUwt3Gm0AZZ2jvOzNjgYuVwMqcDRYwPC+KM6Bb7GUjgB/CzT2wnaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"001139729c6ac196bde858bcaf06938c2eb0aa1eee8fb3166df1baeb87c102d9","last_reissued_at":"2026-07-05T10:03:09.002204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:09.002204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MASS: Overcoming Language Bias in Image-Text Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiwan Chung, Sangkyu Lee, Seungwon Lim, Youngjae Yu","submitted_at":"2025-01-20T12:56:28Z","abstract_excerpt":"Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language priors and neglect to adequately consider the visual content. We thus present Multimodal ASsociation Score (MASS), a framework that reduces the reliance on language priors for better visual accuracy in image-text matching problems. It can be seamlessly incorporated into existing visual-language models without necessitating additional training. Our experiments"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11469","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/2501.11469/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":"2501.11469","created_at":"2026-07-05T10:03:09.002265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11469v1","created_at":"2026-07-05T10:03:09.002265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11469","created_at":"2026-07-05T10:03:09.002265+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAITS4U4NLAZ","created_at":"2026-07-05T10:03:09.002265+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAITS4U4NLAZNPPI","created_at":"2026-07-05T10:03:09.002265+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAITS4U4","created_at":"2026-07-05T10:03:09.002265+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/AAITS4U4NLAZNPPILC6K6BUTRQ","json":"https://pith.science/pith/AAITS4U4NLAZNPPILC6K6BUTRQ.json","graph_json":"https://pith.science/api/pith-number/AAITS4U4NLAZNPPILC6K6BUTRQ/graph.json","events_json":"https://pith.science/api/pith-number/AAITS4U4NLAZNPPILC6K6BUTRQ/events.json","paper":"https://pith.science/paper/AAITS4U4"},"agent_actions":{"view_html":"https://pith.science/pith/AAITS4U4NLAZNPPILC6K6BUTRQ","download_json":"https://pith.science/pith/AAITS4U4NLAZNPPILC6K6BUTRQ.json","view_paper":"https://pith.science/paper/AAITS4U4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11469&json=true","fetch_graph":"https://pith.science/api/pith-number/AAITS4U4NLAZNPPILC6K6BUTRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AAITS4U4NLAZNPPILC6K6BUTRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAITS4U4NLAZNPPILC6K6BUTRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAITS4U4NLAZNPPILC6K6BUTRQ/action/storage_attestation","attest_author":"https://pith.science/pith/AAITS4U4NLAZNPPILC6K6BUTRQ/action/author_attestation","sign_citation":"https://pith.science/pith/AAITS4U4NLAZNPPILC6K6BUTRQ/action/citation_signature","submit_replication":"https://pith.science/pith/AAITS4U4NLAZNPPILC6K6BUTRQ/action/replication_record"}},"created_at":"2026-07-05T10:03:09.002265+00:00","updated_at":"2026-07-05T10:03:09.002265+00:00"}