{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F2HZNZIH4MWAT4F36CYJQFKHNL","short_pith_number":"pith:F2HZNZIH","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"},"canonical_sha256":"2e8f96e507e32c09f0bbf0b09815476afe5324fcc59550823e28b0cdfde86569","source":{"kind":"arxiv","id":"2501.05690","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05690","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05690v1","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05690","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"F2HZNZIH4MWA","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"F2HZNZIH4MWAT4F3","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"F2HZNZIH","created_at":"2026-07-05T09:59:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F2HZNZIH4MWAT4F36CYJQFKHNL","target":"record","payload":{"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"},"canonical_sha256":"2e8f96e507e32c09f0bbf0b09815476afe5324fcc59550823e28b0cdfde86569","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"},"source_kind":"arxiv","source_id":"2501.05690","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZjmOgkqnG5FxVAMjUpQ4sX8AEv8dh4jTt3qXEwWPuJRPD8XahAsvBm1uTOo32MeEAglhnWy9N8IxafL0s2eTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:14:16.347753Z"},"content_sha256":"98fdc2231f62b903e0608cdd2960be80b0bae10cbadb76ce872f54c4f46fbf76","schema_version":"1.0","event_id":"sha256:98fdc2231f62b903e0608cdd2960be80b0bae10cbadb76ce872f54c4f46fbf76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F2HZNZIH4MWAT4F36CYJQFKHNL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dYw5vBD68snlgVsiUM8+Xhv6tQ1VMaQDXgojGg/+9KbObN94w227/CZ/s8SEGqW2OI4PHVaG+o7oyYpu/BLdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:14:16.348635Z"},"content_sha256":"acd3e67758421fae55f10168f96d18a28b028c6b3180679e5794cd04e4fbfac9","schema_version":"1.0","event_id":"sha256:acd3e67758421fae55f10168f96d18a28b028c6b3180679e5794cd04e4fbfac9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/bundle.json","state_url":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/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":"2026-08-10T20:14:16Z","links":{"resolver":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL","bundle":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/bundle.json","state":"https://pith.science/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F2HZNZIH4MWAT4F36CYJQFKHNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F2HZNZIH4MWAT4F36CYJQFKHNL","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":"1a7522fc76828145fd688d7e9b32716203280bad03cdd8a249363247e8e59b2b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T03:42:37Z","title_canon_sha256":"aa74a1ccfd43d9d78406e82cb6db35ffe2763c942b5179f88ff5fce2be0cab84"},"schema_version":"1.0","source":{"id":"2501.05690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05690","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05690v1","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05690","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"F2HZNZIH4MWA","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"F2HZNZIH4MWAT4F3","created_at":"2026-07-05T09:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"F2HZNZIH","created_at":"2026-07-05T09:59:27Z"}],"graph_snapshots":[{"event_id":"sha256:acd3e67758421fae55f10168f96d18a28b028c6b3180679e5794cd04e4fbfac9","target":"graph","created_at":"2026-07-05T09:59:27Z","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/2501.05690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Daowan Peng, Wei Wei","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T03:42:37Z","title":"Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05690","kind":"arxiv","version":1},"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":"sha256:98fdc2231f62b903e0608cdd2960be80b0bae10cbadb76ce872f54c4f46fbf76","target":"record","created_at":"2026-07-05T09:59:27Z","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":"1a7522fc76828145fd688d7e9b32716203280bad03cdd8a249363247e8e59b2b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T03:42:37Z","title_canon_sha256":"aa74a1ccfd43d9d78406e82cb6db35ffe2763c942b5179f88ff5fce2be0cab84"},"schema_version":"1.0","source":{"id":"2501.05690","kind":"arxiv","version":1}},"canonical_sha256":"2e8f96e507e32c09f0bbf0b09815476afe5324fcc59550823e28b0cdfde86569","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e8f96e507e32c09f0bbf0b09815476afe5324fcc59550823e28b0cdfde86569","first_computed_at":"2026-07-05T09:59:27.130310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:27.130310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jeBbEt7F63ECJKrXkXLpG3h9PXO9uQiPusdpMALKHN+tLFiSBKHs6jF9LsL0HbfF69lUWRY+ykYlmXeFfT9SCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:27.130707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98fdc2231f62b903e0608cdd2960be80b0bae10cbadb76ce872f54c4f46fbf76","sha256:acd3e67758421fae55f10168f96d18a28b028c6b3180679e5794cd04e4fbfac9"],"state_sha256":"088b61a8c7f700ebbd875c7f432fb1d06cb1b8305b789b8158ba6b3340cd61d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HhsIDqPt3tLMnkU8pMlbKpVqiKc0HXZPryPrjGeLeV5qTO+bYEVtWHdWWWAwm9Klfanlgvw0h0xL4dwVKrrPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:14:16.356708Z","bundle_sha256":"daf81154a2551cf35437a906e5d3bce4f876da5ebce1488f03d869a77560f688"}}