{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4OU7YPL56CJVBHJGZQKIULZIKC","short_pith_number":"pith:4OU7YPL5","schema_version":"1.0","canonical_sha256":"e3a9fc3d7df093509d26cc148a2f285088b7f4b48ab494df5e9cff9e764d5377","source":{"kind":"arxiv","id":"2112.01955","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Qi Pang, Shuai Wang, Yuanyuan Yuan","submitted_at":"2021-12-03T15:01:52Z","abstract_excerpt":"Various deep neural network (DNN) coverage criteria have been proposed to assess DNN test inputs and steer input mutations. The coverage is characterized via neurons having certain outputs, or the discrepancy between neuron outputs. Nevertheless, recent research indicates that neuron coverage criteria show little correlation with test suite quality.\n  In general, DNNs approximate distributions, by incorporating hierarchical layers, to make predictions for inputs. Thus, we champion to deduce DNN behaviors based on its approximated distributions from a layer perspective. A test suite should be a"},"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":"2112.01955","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-03T15:01:52Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"b7be1b9651eb898ff5b878011f996b7a063c28611568851ac4724c481708960b","abstract_canon_sha256":"7c6ec690e7fe4615ac99e142485549be3d453be91d92a43235128e36b96cc7f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:47.524543Z","signature_b64":"e/MV/1MN5kVqHW2iJITsKr6Y2JErYmRwlcBzPTLLBvKPkYQQimlQqPBkjbVRaYy2/02RSxufu+maTIph+lSmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3a9fc3d7df093509d26cc148a2f285088b7f4b48ab494df5e9cff9e764d5377","last_reissued_at":"2026-07-05T05:25:47.524052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:47.524052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Qi Pang, Shuai Wang, Yuanyuan Yuan","submitted_at":"2021-12-03T15:01:52Z","abstract_excerpt":"Various deep neural network (DNN) coverage criteria have been proposed to assess DNN test inputs and steer input mutations. The coverage is characterized via neurons having certain outputs, or the discrepancy between neuron outputs. Nevertheless, recent research indicates that neuron coverage criteria show little correlation with test suite quality.\n  In general, DNNs approximate distributions, by incorporating hierarchical layers, to make predictions for inputs. Thus, we champion to deduce DNN behaviors based on its approximated distributions from a layer perspective. A test suite should be a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01955","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/2112.01955/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":"2112.01955","created_at":"2026-07-05T05:25:47.524110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.01955v2","created_at":"2026-07-05T05:25:47.524110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01955","created_at":"2026-07-05T05:25:47.524110+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OU7YPL56CJV","created_at":"2026-07-05T05:25:47.524110+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OU7YPL56CJVBHJG","created_at":"2026-07-05T05:25:47.524110+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OU7YPL5","created_at":"2026-07-05T05:25:47.524110+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/4OU7YPL56CJVBHJGZQKIULZIKC","json":"https://pith.science/pith/4OU7YPL56CJVBHJGZQKIULZIKC.json","graph_json":"https://pith.science/api/pith-number/4OU7YPL56CJVBHJGZQKIULZIKC/graph.json","events_json":"https://pith.science/api/pith-number/4OU7YPL56CJVBHJGZQKIULZIKC/events.json","paper":"https://pith.science/paper/4OU7YPL5"},"agent_actions":{"view_html":"https://pith.science/pith/4OU7YPL56CJVBHJGZQKIULZIKC","download_json":"https://pith.science/pith/4OU7YPL56CJVBHJGZQKIULZIKC.json","view_paper":"https://pith.science/paper/4OU7YPL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.01955&json=true","fetch_graph":"https://pith.science/api/pith-number/4OU7YPL56CJVBHJGZQKIULZIKC/graph.json","fetch_events":"https://pith.science/api/pith-number/4OU7YPL56CJVBHJGZQKIULZIKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OU7YPL56CJVBHJGZQKIULZIKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OU7YPL56CJVBHJGZQKIULZIKC/action/storage_attestation","attest_author":"https://pith.science/pith/4OU7YPL56CJVBHJGZQKIULZIKC/action/author_attestation","sign_citation":"https://pith.science/pith/4OU7YPL56CJVBHJGZQKIULZIKC/action/citation_signature","submit_replication":"https://pith.science/pith/4OU7YPL56CJVBHJGZQKIULZIKC/action/replication_record"}},"created_at":"2026-07-05T05:25:47.524110+00:00","updated_at":"2026-07-05T05:25:47.524110+00:00"}