{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G6E75I4I2NFKTIMZRGP63OBB3J","short_pith_number":"pith:G6E75I4I","schema_version":"1.0","canonical_sha256":"3789fea388d34aa9a199899fedb821da558f6ac6042a9b2b3a5cc036c8423d0a","source":{"kind":"arxiv","id":"2310.13073","version":1},"attestation_state":"computed","paper":{"title":"Using Logic Programming and Kernel-Grouping for Improving Interpretability of Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Gopal Gupta, Parth Padalkar","submitted_at":"2023-10-19T18:12:49Z","abstract_excerpt":"Within the realm of deep learning, the interpretability of Convolutional Neural Networks (CNNs), particularly in the context of image classification tasks, remains a formidable challenge. To this end we present a neurosymbolic framework, NeSyFOLD-G that generates a symbolic rule-set using the last layer kernels of the CNN to make its underlying knowledge interpretable. What makes NeSyFOLD-G different from other similar frameworks is that we first find groups of similar kernels in the CNN (kernel-grouping) using the cosine-similarity between the feature maps generated by various kernels. Once s"},"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":"2310.13073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T18:12:49Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d608cb4dc2f4e36d8fdd77f707ce0b7ccfca62eaf1820151b0f817c3eea7351f","abstract_canon_sha256":"550ee3b79d0ac26953f7c018084d629e0f9f83545a6e5a26fde2c9f5b5ed344e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:56.812759Z","signature_b64":"CfjSsV9Zaf3BrSR3poP2cbSBmx/i0deu2zPMwIyZsY0fVAbRsYbmtFeMw1AosXaojnmXqRm+QvK72TBTJUFMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3789fea388d34aa9a199899fedb821da558f6ac6042a9b2b3a5cc036c8423d0a","last_reissued_at":"2026-07-05T07:02:56.812172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:56.812172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Logic Programming and Kernel-Grouping for Improving Interpretability of Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Gopal Gupta, Parth Padalkar","submitted_at":"2023-10-19T18:12:49Z","abstract_excerpt":"Within the realm of deep learning, the interpretability of Convolutional Neural Networks (CNNs), particularly in the context of image classification tasks, remains a formidable challenge. To this end we present a neurosymbolic framework, NeSyFOLD-G that generates a symbolic rule-set using the last layer kernels of the CNN to make its underlying knowledge interpretable. What makes NeSyFOLD-G different from other similar frameworks is that we first find groups of similar kernels in the CNN (kernel-grouping) using the cosine-similarity between the feature maps generated by various kernels. Once s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13073","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/2310.13073/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":"2310.13073","created_at":"2026-07-05T07:02:56.812261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13073v1","created_at":"2026-07-05T07:02:56.812261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13073","created_at":"2026-07-05T07:02:56.812261+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6E75I4I2NFK","created_at":"2026-07-05T07:02:56.812261+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6E75I4I2NFKTIMZ","created_at":"2026-07-05T07:02:56.812261+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6E75I4I","created_at":"2026-07-05T07:02:56.812261+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/G6E75I4I2NFKTIMZRGP63OBB3J","json":"https://pith.science/pith/G6E75I4I2NFKTIMZRGP63OBB3J.json","graph_json":"https://pith.science/api/pith-number/G6E75I4I2NFKTIMZRGP63OBB3J/graph.json","events_json":"https://pith.science/api/pith-number/G6E75I4I2NFKTIMZRGP63OBB3J/events.json","paper":"https://pith.science/paper/G6E75I4I"},"agent_actions":{"view_html":"https://pith.science/pith/G6E75I4I2NFKTIMZRGP63OBB3J","download_json":"https://pith.science/pith/G6E75I4I2NFKTIMZRGP63OBB3J.json","view_paper":"https://pith.science/paper/G6E75I4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13073&json=true","fetch_graph":"https://pith.science/api/pith-number/G6E75I4I2NFKTIMZRGP63OBB3J/graph.json","fetch_events":"https://pith.science/api/pith-number/G6E75I4I2NFKTIMZRGP63OBB3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6E75I4I2NFKTIMZRGP63OBB3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6E75I4I2NFKTIMZRGP63OBB3J/action/storage_attestation","attest_author":"https://pith.science/pith/G6E75I4I2NFKTIMZRGP63OBB3J/action/author_attestation","sign_citation":"https://pith.science/pith/G6E75I4I2NFKTIMZRGP63OBB3J/action/citation_signature","submit_replication":"https://pith.science/pith/G6E75I4I2NFKTIMZRGP63OBB3J/action/replication_record"}},"created_at":"2026-07-05T07:02:56.812261+00:00","updated_at":"2026-07-05T07:02:56.812261+00:00"}