{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F2HZNZIH4MWAT4F36CYJQFKHNL","short_pith_number":"pith:F2HZNZIH","schema_version":"1.0","canonical_sha256":"2e8f96e507e32c09f0bbf0b09815476afe5324fcc59550823e28b0cdfde86569","source":{"kind":"arxiv","id":"2501.05690","version":1},"attestation_state":"computed","paper":{"title":"Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Daowan Peng, Wei Wei","submitted_at":"2025-01-10T03:42:37Z","abstract_excerpt":"Previous studies have pointed out that visual question answering (VQA) models are prone to relying on language priors for answer predictions. In this context, predictions often depend on linguistic shortcuts rather than a comprehensive grasp of multimodal knowledge, which diminishes their generalization ability. In this paper, we propose a novel method, namely, KDAR, leveraging knowledge distillation to address the prior-dependency dilemmas within the VQA task. Specifically, the regularization effect facilitated by soft labels from a well-trained teacher is employed to penalize overfitting to "},"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":"2501.05690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T03:42:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"aa74a1ccfd43d9d78406e82cb6db35ffe2763c942b5179f88ff5fce2be0cab84","abstract_canon_sha256":"1a7522fc76828145fd688d7e9b32716203280bad03cdd8a249363247e8e59b2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:27.130707Z","signature_b64":"jeBbEt7F63ECJKrXkXLpG3h9PXO9uQiPusdpMALKHN+tLFiSBKHs6jF9LsL0HbfF69lUWRY+ykYlmXeFfT9SCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e8f96e507e32c09f0bbf0b09815476afe5324fcc59550823e28b0cdfde86569","last_reissued_at":"2026-07-05T09:59:27.130310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:27.130310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Daowan Peng, Wei Wei","submitted_at":"2025-01-10T03:42:37Z","abstract_excerpt":"Previous studies have pointed out that visual question answering (VQA) models are prone to relying on language priors for answer predictions. In this context, predictions often depend on linguistic shortcuts rather than a comprehensive grasp of multimodal knowledge, which diminishes their generalization ability. In this paper, we propose a novel method, namely, KDAR, leveraging knowledge distillation to address the prior-dependency dilemmas within the VQA task. Specifically, the regularization effect facilitated by soft labels from a well-trained teacher is employed to penalize overfitting to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05690","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/2501.05690/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":"2501.05690","created_at":"2026-07-05T09:59:27.130375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05690v1","created_at":"2026-07-05T09:59:27.130375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05690","created_at":"2026-07-05T09:59:27.130375+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2HZNZIH4MWA","created_at":"2026-07-05T09:59:27.130375+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2HZNZIH4MWAT4F3","created_at":"2026-07-05T09:59:27.130375+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2HZNZIH","created_at":"2026-07-05T09:59:27.130375+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/F2HZNZIH4MWAT4F36CYJQFKHNL","json":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL.json","graph_json":"https://pith.science/api/pith-number/F2HZNZIH4MWAT4F36CYJQFKHNL/graph.json","events_json":"https://pith.science/api/pith-number/F2HZNZIH4MWAT4F36CYJQFKHNL/events.json","paper":"https://pith.science/paper/F2HZNZIH"},"agent_actions":{"view_html":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL","download_json":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL.json","view_paper":"https://pith.science/paper/F2HZNZIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05690&json=true","fetch_graph":"https://pith.science/api/pith-number/F2HZNZIH4MWAT4F36CYJQFKHNL/graph.json","fetch_events":"https://pith.science/api/pith-number/F2HZNZIH4MWAT4F36CYJQFKHNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/action/storage_attestation","attest_author":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/action/author_attestation","sign_citation":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/action/citation_signature","submit_replication":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/action/replication_record"}},"created_at":"2026-07-05T09:59:27.130375+00:00","updated_at":"2026-07-05T09:59:27.130375+00:00"}