{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ISVLKDYFJP4XDND66RYICTXNRU","short_pith_number":"pith:ISVLKDYF","schema_version":"1.0","canonical_sha256":"44aab50f054bf971b47ef470814eed8d37451123f47b6d80507639b8e158a5ca","source":{"kind":"arxiv","id":"2105.08589","version":2},"attestation_state":"computed","paper":{"title":"Self-interpretable Convolutional Neural Networks for Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agus Sudjianto, Rahul Singh, Tarun Joshi, Vijayan N. Nair, Wei Zhao","submitted_at":"2021-05-18T15:19:59Z","abstract_excerpt":"Deep learning models for natural language processing (NLP) are inherently complex and often viewed as black box in nature. This paper develops an approach for interpreting convolutional neural networks for text classification problems by exploiting the local-linear models inherent in ReLU-DNNs. The CNN model combines the word embedding through convolutional layers, filters them using max-pooling, and optimizes using a ReLU-DNN for classification. To get an overall self-interpretable model, the system of local linear models from the ReLU DNN are mapped back through the max-pool filter to the ap"},"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":"2105.08589","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-18T15:19:59Z","cross_cats_sorted":[],"title_canon_sha256":"4a828d94be4660d8192c6d68cf5bb109985e78cc550b53d1e33ec7a133940284","abstract_canon_sha256":"1aaee1be78a1b7361f730b46c091f83702c29361e4d8574df8888c31e1f2fa5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:28.049105Z","signature_b64":"Ph8eT8kSzJTsmqHPDr2Fg2tBPeXJmyY/Hi7VpFF+5zcxRvlZ9ffs0HTjio5zyzMm4t0X1pjZ/lN99Y2b4vyUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44aab50f054bf971b47ef470814eed8d37451123f47b6d80507639b8e158a5ca","last_reissued_at":"2026-07-05T02:56:28.048644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:28.048644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-interpretable Convolutional Neural Networks for Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agus Sudjianto, Rahul Singh, Tarun Joshi, Vijayan N. Nair, Wei Zhao","submitted_at":"2021-05-18T15:19:59Z","abstract_excerpt":"Deep learning models for natural language processing (NLP) are inherently complex and often viewed as black box in nature. This paper develops an approach for interpreting convolutional neural networks for text classification problems by exploiting the local-linear models inherent in ReLU-DNNs. The CNN model combines the word embedding through convolutional layers, filters them using max-pooling, and optimizes using a ReLU-DNN for classification. To get an overall self-interpretable model, the system of local linear models from the ReLU DNN are mapped back through the max-pool filter to the ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08589","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/2105.08589/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":"2105.08589","created_at":"2026-07-05T02:56:28.048702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08589v2","created_at":"2026-07-05T02:56:28.048702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08589","created_at":"2026-07-05T02:56:28.048702+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISVLKDYFJP4X","created_at":"2026-07-05T02:56:28.048702+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISVLKDYFJP4XDND6","created_at":"2026-07-05T02:56:28.048702+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISVLKDYF","created_at":"2026-07-05T02:56:28.048702+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/ISVLKDYFJP4XDND66RYICTXNRU","json":"https://pith.science/pith/ISVLKDYFJP4XDND66RYICTXNRU.json","graph_json":"https://pith.science/api/pith-number/ISVLKDYFJP4XDND66RYICTXNRU/graph.json","events_json":"https://pith.science/api/pith-number/ISVLKDYFJP4XDND66RYICTXNRU/events.json","paper":"https://pith.science/paper/ISVLKDYF"},"agent_actions":{"view_html":"https://pith.science/pith/ISVLKDYFJP4XDND66RYICTXNRU","download_json":"https://pith.science/pith/ISVLKDYFJP4XDND66RYICTXNRU.json","view_paper":"https://pith.science/paper/ISVLKDYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08589&json=true","fetch_graph":"https://pith.science/api/pith-number/ISVLKDYFJP4XDND66RYICTXNRU/graph.json","fetch_events":"https://pith.science/api/pith-number/ISVLKDYFJP4XDND66RYICTXNRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISVLKDYFJP4XDND66RYICTXNRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISVLKDYFJP4XDND66RYICTXNRU/action/storage_attestation","attest_author":"https://pith.science/pith/ISVLKDYFJP4XDND66RYICTXNRU/action/author_attestation","sign_citation":"https://pith.science/pith/ISVLKDYFJP4XDND66RYICTXNRU/action/citation_signature","submit_replication":"https://pith.science/pith/ISVLKDYFJP4XDND66RYICTXNRU/action/replication_record"}},"created_at":"2026-07-05T02:56:28.048702+00:00","updated_at":"2026-07-05T02:56:28.048702+00:00"}