{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IJVUI7F2BT32PT23AIE45GHTNH","short_pith_number":"pith:IJVUI7F2","schema_version":"1.0","canonical_sha256":"426b447cba0cf7a7cf5b0209ce98f369f3014246ee8918aa702dec22ca368ea5","source":{"kind":"arxiv","id":"1907.02711","version":1},"attestation_state":"computed","paper":{"title":"Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Archan Misra, Lakmal Meegahapola, Lance Kaplan, Vengateswaran Subramaniam","submitted_at":"2019-07-05T07:55:09Z","abstract_excerpt":"In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units of a Deep Neural Network used for classification tasks. We show that the combined neural activations of such a hidden layer have class-specific distributional properties, and then define multiple statistical measures to compute how far a test sample's activations deviate from such distributions. Using a variety of benchmark datasets (including MNIST, CIFAR10, Fashion-MNIST & notMNIST), we show how such PAD-based mea"},"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":"1907.02711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-05T07:55:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5248f174c5b7cf64335b8c40ea4b02a5c2b721e6416b762016cd88b5a062172","abstract_canon_sha256":"d3e051a3fca368fde47c85c5627af07f792fd18e35faced369f8476b69edcd5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:23.408539Z","signature_b64":"tmL5ECpxZpV64aAXo5hymdxtQKkRMV7C+iAuREURemH7buKH+9IQvRWVCd1JHJOySuuXNdZ7boEFOAhvagqFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"426b447cba0cf7a7cf5b0209ce98f369f3014246ee8918aa702dec22ca368ea5","last_reissued_at":"2026-05-17T23:41:23.407661Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:23.407661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Archan Misra, Lakmal Meegahapola, Lance Kaplan, Vengateswaran Subramaniam","submitted_at":"2019-07-05T07:55:09Z","abstract_excerpt":"In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units of a Deep Neural Network used for classification tasks. We show that the combined neural activations of such a hidden layer have class-specific distributional properties, and then define multiple statistical measures to compute how far a test sample's activations deviate from such distributions. Using a variety of benchmark datasets (including MNIST, CIFAR10, Fashion-MNIST & notMNIST), we show how such PAD-based mea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02711","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":""},"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":"1907.02711","created_at":"2026-05-17T23:41:23.407798+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02711v1","created_at":"2026-05-17T23:41:23.407798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02711","created_at":"2026-05-17T23:41:23.407798+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJVUI7F2BT32","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJVUI7F2BT32PT23","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJVUI7F2","created_at":"2026-05-18T12:33:18.533446+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/IJVUI7F2BT32PT23AIE45GHTNH","json":"https://pith.science/pith/IJVUI7F2BT32PT23AIE45GHTNH.json","graph_json":"https://pith.science/api/pith-number/IJVUI7F2BT32PT23AIE45GHTNH/graph.json","events_json":"https://pith.science/api/pith-number/IJVUI7F2BT32PT23AIE45GHTNH/events.json","paper":"https://pith.science/paper/IJVUI7F2"},"agent_actions":{"view_html":"https://pith.science/pith/IJVUI7F2BT32PT23AIE45GHTNH","download_json":"https://pith.science/pith/IJVUI7F2BT32PT23AIE45GHTNH.json","view_paper":"https://pith.science/paper/IJVUI7F2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02711&json=true","fetch_graph":"https://pith.science/api/pith-number/IJVUI7F2BT32PT23AIE45GHTNH/graph.json","fetch_events":"https://pith.science/api/pith-number/IJVUI7F2BT32PT23AIE45GHTNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJVUI7F2BT32PT23AIE45GHTNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJVUI7F2BT32PT23AIE45GHTNH/action/storage_attestation","attest_author":"https://pith.science/pith/IJVUI7F2BT32PT23AIE45GHTNH/action/author_attestation","sign_citation":"https://pith.science/pith/IJVUI7F2BT32PT23AIE45GHTNH/action/citation_signature","submit_replication":"https://pith.science/pith/IJVUI7F2BT32PT23AIE45GHTNH/action/replication_record"}},"created_at":"2026-05-17T23:41:23.407798+00:00","updated_at":"2026-05-17T23:41:23.407798+00:00"}