{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5SVA4UFKF63IUXQPES7LG3GNRL","short_pith_number":"pith:5SVA4UFK","schema_version":"1.0","canonical_sha256":"ecaa0e50aa2fb68a5e0f24beb36ccd8ac2e1a5550e29120135a013e6d7fbaf5c","source":{"kind":"arxiv","id":"2308.13651","version":5},"attestation_state":"computed","paper":{"title":"PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Anh Totti Nguyen, Giang (Dexter) Nguyen, Mohammad Reza Taesiri, Valerie Chen","submitted_at":"2023-08-25T19:40:56Z","abstract_excerpt":"Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model's decision. In this paper, we show a novel utility of nearest neighbors: To improve predictions of a frozen, pretrained image classifier C. We leverage an image comparator S that (1) compares the input image with NN images from the top-K most probable classes given by C; and (2) uses scores from S to weight the confidence scores of C to refine predictions. Our method consistently improves fine-grained image classifi"},"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":"2308.13651","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T19:40:56Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"4d5d727f06144c528e3c3b35d0f8b4092ce03e98379bce22101340f02d2f2304","abstract_canon_sha256":"e74d93003168aa836ee459e27b76ef9d092b0496d55709a9c1d61ea016ac34cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:23.932872Z","signature_b64":"hyTseKiLyIxbJrqmzWzzBWz6nRSh3zjBeYAhP1BgLDVch3gRnSI+DPKMWtnMls9y/v7AAssNikMFCeuF4FfkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecaa0e50aa2fb68a5e0f24beb36ccd8ac2e1a5550e29120135a013e6d7fbaf5c","last_reissued_at":"2026-07-05T08:59:23.932417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:23.932417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Anh Totti Nguyen, Giang (Dexter) Nguyen, Mohammad Reza Taesiri, Valerie Chen","submitted_at":"2023-08-25T19:40:56Z","abstract_excerpt":"Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model's decision. In this paper, we show a novel utility of nearest neighbors: To improve predictions of a frozen, pretrained image classifier C. We leverage an image comparator S that (1) compares the input image with NN images from the top-K most probable classes given by C; and (2) uses scores from S to weight the confidence scores of C to refine predictions. Our method consistently improves fine-grained image classifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13651","kind":"arxiv","version":5},"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/2308.13651/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":"2308.13651","created_at":"2026-07-05T08:59:23.932477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13651v5","created_at":"2026-07-05T08:59:23.932477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13651","created_at":"2026-07-05T08:59:23.932477+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SVA4UFKF63I","created_at":"2026-07-05T08:59:23.932477+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SVA4UFKF63IUXQP","created_at":"2026-07-05T08:59:23.932477+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SVA4UFK","created_at":"2026-07-05T08:59:23.932477+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/5SVA4UFKF63IUXQPES7LG3GNRL","json":"https://pith.science/pith/5SVA4UFKF63IUXQPES7LG3GNRL.json","graph_json":"https://pith.science/api/pith-number/5SVA4UFKF63IUXQPES7LG3GNRL/graph.json","events_json":"https://pith.science/api/pith-number/5SVA4UFKF63IUXQPES7LG3GNRL/events.json","paper":"https://pith.science/paper/5SVA4UFK"},"agent_actions":{"view_html":"https://pith.science/pith/5SVA4UFKF63IUXQPES7LG3GNRL","download_json":"https://pith.science/pith/5SVA4UFKF63IUXQPES7LG3GNRL.json","view_paper":"https://pith.science/paper/5SVA4UFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13651&json=true","fetch_graph":"https://pith.science/api/pith-number/5SVA4UFKF63IUXQPES7LG3GNRL/graph.json","fetch_events":"https://pith.science/api/pith-number/5SVA4UFKF63IUXQPES7LG3GNRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SVA4UFKF63IUXQPES7LG3GNRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SVA4UFKF63IUXQPES7LG3GNRL/action/storage_attestation","attest_author":"https://pith.science/pith/5SVA4UFKF63IUXQPES7LG3GNRL/action/author_attestation","sign_citation":"https://pith.science/pith/5SVA4UFKF63IUXQPES7LG3GNRL/action/citation_signature","submit_replication":"https://pith.science/pith/5SVA4UFKF63IUXQPES7LG3GNRL/action/replication_record"}},"created_at":"2026-07-05T08:59:23.932477+00:00","updated_at":"2026-07-05T08:59:23.932477+00:00"}