{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PHE3YG2YQ3WIFC5676B2T7G4RX","short_pith_number":"pith:PHE3YG2Y","schema_version":"1.0","canonical_sha256":"79c9bc1b5886ec828bbeff83a9fcdc8ddbbf196d85b0374d084e0a105e8522cd","source":{"kind":"arxiv","id":"1809.06573","version":2},"attestation_state":"computed","paper":{"title":"Runtime Monitoring Neuron Activation Patterns","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chih-Hong Cheng, Georg N\\\"uhrenberg, Hirotoshi Yasuoka","submitted_at":"2018-09-18T07:54:43Z","abstract_excerpt":"For using neural networks in safety critical domains, it is important to know if a decision made by a neural network is supported by prior similarities in training. We propose runtime neuron activation pattern monitoring - after the standard training process, one creates a monitor by feeding the training data to the network again in order to store the neuron activation patterns in abstract form. In operation, a classification decision over an input is further supplemented by examining if a pattern similar (measured by Hamming distance) to the generated pattern is contained in the monitor. If t"},"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":"1809.06573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-18T07:54:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9cc49daeb2a01dbbfb12ec5d65bb093212b70b296c07962f3a24792973033f1e","abstract_canon_sha256":"ba56fb878c03225804d8612f6c5b060a56da92789516300e0865e0357d9b4340"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:13.415758Z","signature_b64":"XPPPbaFvr1UD7T2IhFExDSvdUAtYXWlCixpcLBsCmXQ7Df9VnOQIkRx55Fy+xAQmE6gtTaFwuFdH7jQwAjvWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79c9bc1b5886ec828bbeff83a9fcdc8ddbbf196d85b0374d084e0a105e8522cd","last_reissued_at":"2026-05-18T00:05:13.415172Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:13.415172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Runtime Monitoring Neuron Activation Patterns","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chih-Hong Cheng, Georg N\\\"uhrenberg, Hirotoshi Yasuoka","submitted_at":"2018-09-18T07:54:43Z","abstract_excerpt":"For using neural networks in safety critical domains, it is important to know if a decision made by a neural network is supported by prior similarities in training. We propose runtime neuron activation pattern monitoring - after the standard training process, one creates a monitor by feeding the training data to the network again in order to store the neuron activation patterns in abstract form. In operation, a classification decision over an input is further supplemented by examining if a pattern similar (measured by Hamming distance) to the generated pattern is contained in the monitor. If t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06573","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":""},"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":"1809.06573","created_at":"2026-05-18T00:05:13.415266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.06573v2","created_at":"2026-05-18T00:05:13.415266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06573","created_at":"2026-05-18T00:05:13.415266+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHE3YG2YQ3WI","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHE3YG2YQ3WIFC56","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHE3YG2Y","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2410.08491","citing_title":"Edge Case Detection in Automated Driving: Methods, Challenges and Future Directions","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX","json":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX.json","graph_json":"https://pith.science/api/pith-number/PHE3YG2YQ3WIFC5676B2T7G4RX/graph.json","events_json":"https://pith.science/api/pith-number/PHE3YG2YQ3WIFC5676B2T7G4RX/events.json","paper":"https://pith.science/paper/PHE3YG2Y"},"agent_actions":{"view_html":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX","download_json":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX.json","view_paper":"https://pith.science/paper/PHE3YG2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.06573&json=true","fetch_graph":"https://pith.science/api/pith-number/PHE3YG2YQ3WIFC5676B2T7G4RX/graph.json","fetch_events":"https://pith.science/api/pith-number/PHE3YG2YQ3WIFC5676B2T7G4RX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX/action/storage_attestation","attest_author":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX/action/author_attestation","sign_citation":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX/action/citation_signature","submit_replication":"https://pith.science/pith/PHE3YG2YQ3WIFC5676B2T7G4RX/action/replication_record"}},"created_at":"2026-05-18T00:05:13.415266+00:00","updated_at":"2026-05-18T00:05:13.415266+00:00"}