{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KBJQNJFB5UX6SLP2OFHRDA3MFE","short_pith_number":"pith:KBJQNJFB","schema_version":"1.0","canonical_sha256":"505306a4a1ed2fe92dfa714f11836c2932c094968d30b8818f8e969990d33a9b","source":{"kind":"arxiv","id":"2107.08362","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Verification of Neural Networks Against Group Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Bing Sun, Jun Sun, Lijun Zhang, Ting Dai","submitted_at":"2021-07-18T04:34:31Z","abstract_excerpt":"Fairness is crucial for neural networks which are used in applications with important societal implication. Recently, there have been multiple attempts on improving fairness of neural networks, with a focus on fairness testing (e.g., generating individual discriminatory instances) and fairness training (e.g., enhancing fairness through augmented training). In this work, we propose an approach to formally verify neural networks against fairness, with a focus on independence-based fairness such as group fairness. Our method is built upon an approach for learning Markov Chains from a user-provide"},"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":"2107.08362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-18T04:34:31Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"3ff9e0166eb104fbf04b8eb87a27a6aa6a48d6e25dac9cb6c9948d5c9ef1ca06","abstract_canon_sha256":"5fc5b1a6372062c7d7b90f48a8e7846b5e0db24ef2616aaca3155b11e00b9039"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:48.615304Z","signature_b64":"DuQntXR3F6h5YMRO8H11l4andnyG8skeKOtWfn7FGSdGPPx3UWKht3StGHtzSEaSCxi109mkAgL2c4AGFNWwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"505306a4a1ed2fe92dfa714f11836c2932c094968d30b8818f8e969990d33a9b","last_reissued_at":"2026-07-05T02:58:48.614896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:48.614896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Verification of Neural Networks Against Group Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Bing Sun, Jun Sun, Lijun Zhang, Ting Dai","submitted_at":"2021-07-18T04:34:31Z","abstract_excerpt":"Fairness is crucial for neural networks which are used in applications with important societal implication. Recently, there have been multiple attempts on improving fairness of neural networks, with a focus on fairness testing (e.g., generating individual discriminatory instances) and fairness training (e.g., enhancing fairness through augmented training). In this work, we propose an approach to formally verify neural networks against fairness, with a focus on independence-based fairness such as group fairness. Our method is built upon an approach for learning Markov Chains from a user-provide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08362","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/2107.08362/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":"2107.08362","created_at":"2026-07-05T02:58:48.614966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08362v1","created_at":"2026-07-05T02:58:48.614966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08362","created_at":"2026-07-05T02:58:48.614966+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBJQNJFB5UX6","created_at":"2026-07-05T02:58:48.614966+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBJQNJFB5UX6SLP2","created_at":"2026-07-05T02:58:48.614966+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBJQNJFB","created_at":"2026-07-05T02:58:48.614966+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/KBJQNJFB5UX6SLP2OFHRDA3MFE","json":"https://pith.science/pith/KBJQNJFB5UX6SLP2OFHRDA3MFE.json","graph_json":"https://pith.science/api/pith-number/KBJQNJFB5UX6SLP2OFHRDA3MFE/graph.json","events_json":"https://pith.science/api/pith-number/KBJQNJFB5UX6SLP2OFHRDA3MFE/events.json","paper":"https://pith.science/paper/KBJQNJFB"},"agent_actions":{"view_html":"https://pith.science/pith/KBJQNJFB5UX6SLP2OFHRDA3MFE","download_json":"https://pith.science/pith/KBJQNJFB5UX6SLP2OFHRDA3MFE.json","view_paper":"https://pith.science/paper/KBJQNJFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08362&json=true","fetch_graph":"https://pith.science/api/pith-number/KBJQNJFB5UX6SLP2OFHRDA3MFE/graph.json","fetch_events":"https://pith.science/api/pith-number/KBJQNJFB5UX6SLP2OFHRDA3MFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBJQNJFB5UX6SLP2OFHRDA3MFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBJQNJFB5UX6SLP2OFHRDA3MFE/action/storage_attestation","attest_author":"https://pith.science/pith/KBJQNJFB5UX6SLP2OFHRDA3MFE/action/author_attestation","sign_citation":"https://pith.science/pith/KBJQNJFB5UX6SLP2OFHRDA3MFE/action/citation_signature","submit_replication":"https://pith.science/pith/KBJQNJFB5UX6SLP2OFHRDA3MFE/action/replication_record"}},"created_at":"2026-07-05T02:58:48.614966+00:00","updated_at":"2026-07-05T02:58:48.614966+00:00"}