{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:266S2OMCVSSWCR72T6BC5EH62N","short_pith_number":"pith:266S2OMC","schema_version":"1.0","canonical_sha256":"d7bd2d3982aca56147fa9f822e90fed3516d62d15ef8b8cce10f521b41cccfc5","source":{"kind":"arxiv","id":"2112.02902","version":2},"attestation_state":"computed","paper":{"title":"Interpretable Image Classification with Differentiable Prototypes Assignment","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, {\\L}ukasz Struski, Micha{\\l} G\\'orszczak","submitted_at":"2021-12-06T10:03:32Z","abstract_excerpt":"We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruning stage. It is obtained by introducing a fully differentiable assignment of prototypes to particular classes. Moreover, we introduce a novel focal similarity function to focus the model on the rare foreground features. We show that ProtoPool obtains state-of-the-art accuracy on the CUB-200-2011 and the Stanford Cars datasets, substantially reducing the number of prototypes. We"},"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":"2112.02902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-06T10:03:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ad0e8691c7b3a8edfe8f546027638099aadd092e188b1c1f6483e295ba40e9c6","abstract_canon_sha256":"51e283f14f1b6ffa20fdf3e33e2abf3cb8a8092ad82fdf973339d7a998aa1e5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:17.276970Z","signature_b64":"lmkLp4M+nusDrGjhfhvspR6sPahsHoGczoRO9jPeDkMwUxlaOoK1MMFK7zFX0iH9zCkhpYH1hYikc/dy+hRQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7bd2d3982aca56147fa9f822e90fed3516d62d15ef8b8cce10f521b41cccfc5","last_reissued_at":"2026-07-05T04:54:17.276518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:17.276518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Image Classification with Differentiable Prototypes Assignment","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, {\\L}ukasz Struski, Micha{\\l} G\\'orszczak","submitted_at":"2021-12-06T10:03:32Z","abstract_excerpt":"We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruning stage. It is obtained by introducing a fully differentiable assignment of prototypes to particular classes. Moreover, we introduce a novel focal similarity function to focus the model on the rare foreground features. We show that ProtoPool obtains state-of-the-art accuracy on the CUB-200-2011 and the Stanford Cars datasets, substantially reducing the number of prototypes. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02902","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/2112.02902/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":"2112.02902","created_at":"2026-07-05T04:54:17.276568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02902v2","created_at":"2026-07-05T04:54:17.276568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02902","created_at":"2026-07-05T04:54:17.276568+00:00"},{"alias_kind":"pith_short_12","alias_value":"266S2OMCVSSW","created_at":"2026-07-05T04:54:17.276568+00:00"},{"alias_kind":"pith_short_16","alias_value":"266S2OMCVSSWCR72","created_at":"2026-07-05T04:54:17.276568+00:00"},{"alias_kind":"pith_short_8","alias_value":"266S2OMC","created_at":"2026-07-05T04:54:17.276568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27582","citing_title":"Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27582","citing_title":"Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N","json":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N.json","graph_json":"https://pith.science/api/pith-number/266S2OMCVSSWCR72T6BC5EH62N/graph.json","events_json":"https://pith.science/api/pith-number/266S2OMCVSSWCR72T6BC5EH62N/events.json","paper":"https://pith.science/paper/266S2OMC"},"agent_actions":{"view_html":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N","download_json":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N.json","view_paper":"https://pith.science/paper/266S2OMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02902&json=true","fetch_graph":"https://pith.science/api/pith-number/266S2OMCVSSWCR72T6BC5EH62N/graph.json","fetch_events":"https://pith.science/api/pith-number/266S2OMCVSSWCR72T6BC5EH62N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N/action/storage_attestation","attest_author":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N/action/author_attestation","sign_citation":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N/action/citation_signature","submit_replication":"https://pith.science/pith/266S2OMCVSSWCR72T6BC5EH62N/action/replication_record"}},"created_at":"2026-07-05T04:54:17.276568+00:00","updated_at":"2026-07-05T04:54:17.276568+00:00"}