{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OR2QB44R64ZJX3YHAELKUGOP6C","short_pith_number":"pith:OR2QB44R","schema_version":"1.0","canonical_sha256":"747500f391f7329bef070116aa19cff087c7e376a295e40555a738e78df64d1f","source":{"kind":"arxiv","id":"1908.04389","version":1},"attestation_state":"computed","paper":{"title":"NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Amy Widdicombe, Mani Srivastava, Moustafa Alzantot, Simon Julier","submitted_at":"2019-08-05T07:33:30Z","abstract_excerpt":"Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their decisions. Over the past few years, researchers have studied the problem of providing explanations of why DNNs predicted their results. However, existing techniques are either obtrusive, requiring changes in model training, or suffer from low output quality. In this paper, we present a novel method, NeuroMask, for generating an interpretable explana"},"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":"1908.04389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-05T07:33:30Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"61a47a650bac73cc368d6d5dc4870a3ff2d96668c2c3505fbd7a0e6a725302f0","abstract_canon_sha256":"d48a3e239ae213acfa947ab13ba553dc771253a2977427ed3ba948636eb87eb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:54:30.329381Z","signature_b64":"9Q080FwNH61F6TxAjeUgdb+e92/GGqByaOwibe8+EDtD6jiJMPYF0ch+TEuibizMBE7lUkoJ21nJWw9YxjpnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"747500f391f7329bef070116aa19cff087c7e376a295e40555a738e78df64d1f","last_reissued_at":"2026-07-04T23:54:30.328964Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:54:30.328964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Amy Widdicombe, Mani Srivastava, Moustafa Alzantot, Simon Julier","submitted_at":"2019-08-05T07:33:30Z","abstract_excerpt":"Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their decisions. Over the past few years, researchers have studied the problem of providing explanations of why DNNs predicted their results. However, existing techniques are either obtrusive, requiring changes in model training, or suffer from low output quality. In this paper, we present a novel method, NeuroMask, for generating an interpretable explana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04389","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/1908.04389/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":"1908.04389","created_at":"2026-07-04T23:54:30.329021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04389v1","created_at":"2026-07-04T23:54:30.329021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04389","created_at":"2026-07-04T23:54:30.329021+00:00"},{"alias_kind":"pith_short_12","alias_value":"OR2QB44R64ZJ","created_at":"2026-07-04T23:54:30.329021+00:00"},{"alias_kind":"pith_short_16","alias_value":"OR2QB44R64ZJX3YH","created_at":"2026-07-04T23:54:30.329021+00:00"},{"alias_kind":"pith_short_8","alias_value":"OR2QB44R","created_at":"2026-07-04T23:54:30.329021+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/OR2QB44R64ZJX3YHAELKUGOP6C","json":"https://pith.science/pith/OR2QB44R64ZJX3YHAELKUGOP6C.json","graph_json":"https://pith.science/api/pith-number/OR2QB44R64ZJX3YHAELKUGOP6C/graph.json","events_json":"https://pith.science/api/pith-number/OR2QB44R64ZJX3YHAELKUGOP6C/events.json","paper":"https://pith.science/paper/OR2QB44R"},"agent_actions":{"view_html":"https://pith.science/pith/OR2QB44R64ZJX3YHAELKUGOP6C","download_json":"https://pith.science/pith/OR2QB44R64ZJX3YHAELKUGOP6C.json","view_paper":"https://pith.science/paper/OR2QB44R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04389&json=true","fetch_graph":"https://pith.science/api/pith-number/OR2QB44R64ZJX3YHAELKUGOP6C/graph.json","fetch_events":"https://pith.science/api/pith-number/OR2QB44R64ZJX3YHAELKUGOP6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OR2QB44R64ZJX3YHAELKUGOP6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OR2QB44R64ZJX3YHAELKUGOP6C/action/storage_attestation","attest_author":"https://pith.science/pith/OR2QB44R64ZJX3YHAELKUGOP6C/action/author_attestation","sign_citation":"https://pith.science/pith/OR2QB44R64ZJX3YHAELKUGOP6C/action/citation_signature","submit_replication":"https://pith.science/pith/OR2QB44R64ZJX3YHAELKUGOP6C/action/replication_record"}},"created_at":"2026-07-04T23:54:30.329021+00:00","updated_at":"2026-07-04T23:54:30.329021+00:00"}