{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WV67XUVF3MO7C4WPVFX3HWEBDR","short_pith_number":"pith:WV67XUVF","schema_version":"1.0","canonical_sha256":"b57dfbd2a5db1df172cfa96fb3d8811c53d74af01685ab63118f1f11bab20950","source":{"kind":"arxiv","id":"2401.08169","version":2},"attestation_state":"computed","paper":{"title":"Statistical Test for Attention Map in Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daiki Miwa, Ichiro Takeuchi, Kouichi Taji, Teruyuki Katsuoka, Tomohiro Shiraishi, Vo Nguyen Le Duy","submitted_at":"2024-01-16T07:18:47Z","abstract_excerpt":"The Vision Transformer (ViT) demonstrates exceptional performance in various computer vision tasks. Attention is crucial for ViT to capture complex wide-ranging relationships among image patches, allowing the model to weigh the importance of image patches and aiding our understanding of the decision-making process. However, when utilizing the attention of ViT as evidence in high-stakes decision-making tasks such as medical diagnostics, a challenge arises due to the potential of attention mechanisms erroneously focusing on irrelevant regions. In this study, we propose a statistical test for ViT"},"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":"2401.08169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-01-16T07:18:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e551e1ef713a8dba098c2a5cd6b8c4d98fc99af7dfc339f3fc112b025f140c12","abstract_canon_sha256":"2d0a365eb696f223eb0a9a0b83f32356ec2d0fa753ebdf20c29747cf9ff5bd93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:24.386120Z","signature_b64":"caGfBHXC8Sl7pFWwyxerwt3RWRdFfspnSwy73AHVMlUIIQx6jtvtbKa7MDHgHZgmhelUhP31Wyuo0RWDeRtXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b57dfbd2a5db1df172cfa96fb3d8811c53d74af01685ab63118f1f11bab20950","last_reissued_at":"2026-07-05T07:35:24.385645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:24.385645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Test for Attention Map in Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daiki Miwa, Ichiro Takeuchi, Kouichi Taji, Teruyuki Katsuoka, Tomohiro Shiraishi, Vo Nguyen Le Duy","submitted_at":"2024-01-16T07:18:47Z","abstract_excerpt":"The Vision Transformer (ViT) demonstrates exceptional performance in various computer vision tasks. Attention is crucial for ViT to capture complex wide-ranging relationships among image patches, allowing the model to weigh the importance of image patches and aiding our understanding of the decision-making process. However, when utilizing the attention of ViT as evidence in high-stakes decision-making tasks such as medical diagnostics, a challenge arises due to the potential of attention mechanisms erroneously focusing on irrelevant regions. In this study, we propose a statistical test for ViT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08169","kind":"arxiv","version":2},"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/2401.08169/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":"2401.08169","created_at":"2026-07-05T07:35:24.385702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08169v2","created_at":"2026-07-05T07:35:24.385702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08169","created_at":"2026-07-05T07:35:24.385702+00:00"},{"alias_kind":"pith_short_12","alias_value":"WV67XUVF3MO7","created_at":"2026-07-05T07:35:24.385702+00:00"},{"alias_kind":"pith_short_16","alias_value":"WV67XUVF3MO7C4WP","created_at":"2026-07-05T07:35:24.385702+00:00"},{"alias_kind":"pith_short_8","alias_value":"WV67XUVF","created_at":"2026-07-05T07:35:24.385702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18633","citing_title":"Statistical Inference for Clustering-based Anomaly Detection","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR","json":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR.json","graph_json":"https://pith.science/api/pith-number/WV67XUVF3MO7C4WPVFX3HWEBDR/graph.json","events_json":"https://pith.science/api/pith-number/WV67XUVF3MO7C4WPVFX3HWEBDR/events.json","paper":"https://pith.science/paper/WV67XUVF"},"agent_actions":{"view_html":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR","download_json":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR.json","view_paper":"https://pith.science/paper/WV67XUVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08169&json=true","fetch_graph":"https://pith.science/api/pith-number/WV67XUVF3MO7C4WPVFX3HWEBDR/graph.json","fetch_events":"https://pith.science/api/pith-number/WV67XUVF3MO7C4WPVFX3HWEBDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR/action/storage_attestation","attest_author":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR/action/author_attestation","sign_citation":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR/action/citation_signature","submit_replication":"https://pith.science/pith/WV67XUVF3MO7C4WPVFX3HWEBDR/action/replication_record"}},"created_at":"2026-07-05T07:35:24.385702+00:00","updated_at":"2026-07-05T07:35:24.385702+00:00"}