{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XJTDX34TNOPAUMCCSUGX6VMRGO","short_pith_number":"pith:XJTDX34T","schema_version":"1.0","canonical_sha256":"ba663bef936b9e0a3042950d7f559133bc56ed5eea11c6b2ca27a05652d286d0","source":{"kind":"arxiv","id":"2406.14675","version":1},"attestation_state":"computed","paper":{"title":"This Looks Better than That: Better Interpretable Models with ProtoPNeXt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alina Jade Barnett, Cynthia Rudin, Emmanuel Mokel, Frank Willard, Giyoung Kim, Jon Donnelly, Julia Yang, Luke Moffett, Stark Guo","submitted_at":"2024-06-20T18:54:27Z","abstract_excerpt":"Prototypical-part models are a popular interpretable alternative to black-box deep learning models for computer vision. However, they are difficult to train, with high sensitivity to hyperparameter tuning, inhibiting their application to new datasets and our understanding of which methods truly improve their performance. To facilitate the careful study of prototypical-part networks (ProtoPNets), we create a new framework for integrating components of prototypical-part models -- ProtoPNeXt. Using ProtoPNeXt, we show that applying Bayesian hyperparameter tuning and an angular prototype similarit"},"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":"2406.14675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T18:54:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e37edde308e3935c0232d369b176e0411eb1db9ac58d0fd0e7e0fda75ee128fd","abstract_canon_sha256":"d5587a65d06d59a744e1a470fbd0966b08cfc992bcbd77352fa4d78414104587"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:06.731479Z","signature_b64":"VsVFNCk4eV4ExHqamZJ7AAlDPBJ4qJeojW3NhWz7cczF4yiDWCTNBfA643hziK+irFwtekQME1K4vg+USG5OCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba663bef936b9e0a3042950d7f559133bc56ed5eea11c6b2ca27a05652d286d0","last_reissued_at":"2026-07-05T08:35:06.730966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:06.730966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"This Looks Better than That: Better Interpretable Models with ProtoPNeXt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alina Jade Barnett, Cynthia Rudin, Emmanuel Mokel, Frank Willard, Giyoung Kim, Jon Donnelly, Julia Yang, Luke Moffett, Stark Guo","submitted_at":"2024-06-20T18:54:27Z","abstract_excerpt":"Prototypical-part models are a popular interpretable alternative to black-box deep learning models for computer vision. However, they are difficult to train, with high sensitivity to hyperparameter tuning, inhibiting their application to new datasets and our understanding of which methods truly improve their performance. To facilitate the careful study of prototypical-part networks (ProtoPNets), we create a new framework for integrating components of prototypical-part models -- ProtoPNeXt. Using ProtoPNeXt, we show that applying Bayesian hyperparameter tuning and an angular prototype similarit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14675","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/2406.14675/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":"2406.14675","created_at":"2026-07-05T08:35:06.731021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14675v1","created_at":"2026-07-05T08:35:06.731021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14675","created_at":"2026-07-05T08:35:06.731021+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJTDX34TNOPA","created_at":"2026-07-05T08:35:06.731021+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJTDX34TNOPAUMCC","created_at":"2026-07-05T08:35:06.731021+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJTDX34T","created_at":"2026-07-05T08:35:06.731021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00510","citing_title":"Prototype Language Models","ref_index":215,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO","json":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO.json","graph_json":"https://pith.science/api/pith-number/XJTDX34TNOPAUMCCSUGX6VMRGO/graph.json","events_json":"https://pith.science/api/pith-number/XJTDX34TNOPAUMCCSUGX6VMRGO/events.json","paper":"https://pith.science/paper/XJTDX34T"},"agent_actions":{"view_html":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO","download_json":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO.json","view_paper":"https://pith.science/paper/XJTDX34T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14675&json=true","fetch_graph":"https://pith.science/api/pith-number/XJTDX34TNOPAUMCCSUGX6VMRGO/graph.json","fetch_events":"https://pith.science/api/pith-number/XJTDX34TNOPAUMCCSUGX6VMRGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO/action/storage_attestation","attest_author":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO/action/author_attestation","sign_citation":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO/action/citation_signature","submit_replication":"https://pith.science/pith/XJTDX34TNOPAUMCCSUGX6VMRGO/action/replication_record"}},"created_at":"2026-07-05T08:35:06.731021+00:00","updated_at":"2026-07-05T08:35:06.731021+00:00"}