{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RONUKL7GBTYRBBVQSKOM4KXETZ","short_pith_number":"pith:RONUKL7G","schema_version":"1.0","canonical_sha256":"8b9b452fe60cf11086b0929cce2ae49e4da1fe400e647751009e7886ac104874","source":{"kind":"arxiv","id":"2405.14331","version":1},"attestation_state":"computed","paper":{"title":"LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bartosz Zieli\\'nski, Dawid Rymarczyk, Jacek Tabor, Koryna Lewandowska, Mateusz Pach","submitted_at":"2024-05-23T09:00:59Z","abstract_excerpt":"Prototypical parts networks combine the power of deep learning with the explainability of case-based reasoning to make accurate, interpretable decisions. They follow the this looks like that reasoning, representing each prototypical part with patches from training images. However, a single image patch comprises multiple visual features, such as color, shape, and texture, making it difficult for users to identify which feature is important to the model.\n  To reduce this ambiguity, we introduce the Lucid Prototypical Parts Network (LucidPPN), a novel prototypical parts network that separates col"},"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":"2405.14331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T09:00:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a1372af8f8eac4fef81c9eb05749c74c4b42898c87d29776c13fc1368285c025","abstract_canon_sha256":"17bcdeea6a93a625d88bea607e145ef1127f70321f3ae74f457e9d6915e5fcad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:13.317220Z","signature_b64":"i9W+L32g6UvNdU8gzaxx94rCI7mn1oXi7rUu1P5wyq8hoZQuD4rJw+kXJiUt6QB1O+f2k2VBCq66Z6fnI0WhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b9b452fe60cf11086b0929cce2ae49e4da1fe400e647751009e7886ac104874","last_reissued_at":"2026-07-05T08:22:13.316795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:13.316795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bartosz Zieli\\'nski, Dawid Rymarczyk, Jacek Tabor, Koryna Lewandowska, Mateusz Pach","submitted_at":"2024-05-23T09:00:59Z","abstract_excerpt":"Prototypical parts networks combine the power of deep learning with the explainability of case-based reasoning to make accurate, interpretable decisions. They follow the this looks like that reasoning, representing each prototypical part with patches from training images. However, a single image patch comprises multiple visual features, such as color, shape, and texture, making it difficult for users to identify which feature is important to the model.\n  To reduce this ambiguity, we introduce the Lucid Prototypical Parts Network (LucidPPN), a novel prototypical parts network that separates col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14331","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/2405.14331/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":"2405.14331","created_at":"2026-07-05T08:22:13.316851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14331v1","created_at":"2026-07-05T08:22:13.316851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14331","created_at":"2026-07-05T08:22:13.316851+00:00"},{"alias_kind":"pith_short_12","alias_value":"RONUKL7GBTYR","created_at":"2026-07-05T08:22:13.316851+00:00"},{"alias_kind":"pith_short_16","alias_value":"RONUKL7GBTYRBBVQ","created_at":"2026-07-05T08:22:13.316851+00:00"},{"alias_kind":"pith_short_8","alias_value":"RONUKL7G","created_at":"2026-07-05T08:22:13.316851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15499","citing_title":"A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ","json":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ.json","graph_json":"https://pith.science/api/pith-number/RONUKL7GBTYRBBVQSKOM4KXETZ/graph.json","events_json":"https://pith.science/api/pith-number/RONUKL7GBTYRBBVQSKOM4KXETZ/events.json","paper":"https://pith.science/paper/RONUKL7G"},"agent_actions":{"view_html":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ","download_json":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ.json","view_paper":"https://pith.science/paper/RONUKL7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14331&json=true","fetch_graph":"https://pith.science/api/pith-number/RONUKL7GBTYRBBVQSKOM4KXETZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RONUKL7GBTYRBBVQSKOM4KXETZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ/action/storage_attestation","attest_author":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ/action/author_attestation","sign_citation":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ/action/citation_signature","submit_replication":"https://pith.science/pith/RONUKL7GBTYRBBVQSKOM4KXETZ/action/replication_record"}},"created_at":"2026-07-05T08:22:13.316851+00:00","updated_at":"2026-07-05T08:22:13.316851+00:00"}