{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NQVPOLWUZHM2WUOEBMQS54ZBYA","short_pith_number":"pith:NQVPOLWU","schema_version":"1.0","canonical_sha256":"6c2af72ed4c9d9ab51c40b212ef321c03eaced92c17192d27980eee11a0edf6a","source":{"kind":"arxiv","id":"2207.03113","version":4},"attestation_state":"computed","paper":{"title":"An Additive Instance-Wise Approach to Multi-class Model Interpretation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dinh Phung, Gholamreza Haffari, Quan Hung Tran, Seyit Camtepe, Trung Le, Van Nguyen, Vy Vo","submitted_at":"2022-07-07T06:50:27Z","abstract_excerpt":"Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying explanatory input features, which generally fall into two main categories: attribution and selection. A popular attribution-based approach is to exploit local neighborhoods for learning instance-specific explainers in an additive manner. The process is thus inefficient and susceptible to poorly-conditioned samples. Meanwhile, many selection-based methods directly optimize local feature distributions in an instance-wise tr"},"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":"2207.03113","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-07T06:50:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0bbfae57f3ea97918ae5a1f46ab4ee09078210f2cc5595b55633ba6681dee645","abstract_canon_sha256":"1e5106c3ade4b05b7d9ec5d26af47d6fe6eff223e965382ceb998f6dee1e52b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:10.837077Z","signature_b64":"v2LGtXHcf3adqdhytYSzbR8MtV4C7JF1VsrBNoglBtfOALCq3hpBFU2z7SPrskK3ulQgOJCqNqcv+qoTfJlmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c2af72ed4c9d9ab51c40b212ef321c03eaced92c17192d27980eee11a0edf6a","last_reissued_at":"2026-07-05T06:16:10.836666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:10.836666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Additive Instance-Wise Approach to Multi-class Model Interpretation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dinh Phung, Gholamreza Haffari, Quan Hung Tran, Seyit Camtepe, Trung Le, Van Nguyen, Vy Vo","submitted_at":"2022-07-07T06:50:27Z","abstract_excerpt":"Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying explanatory input features, which generally fall into two main categories: attribution and selection. A popular attribution-based approach is to exploit local neighborhoods for learning instance-specific explainers in an additive manner. The process is thus inefficient and susceptible to poorly-conditioned samples. Meanwhile, many selection-based methods directly optimize local feature distributions in an instance-wise tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03113","kind":"arxiv","version":4},"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/2207.03113/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":"2207.03113","created_at":"2026-07-05T06:16:10.836723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.03113v4","created_at":"2026-07-05T06:16:10.836723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03113","created_at":"2026-07-05T06:16:10.836723+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQVPOLWUZHM2","created_at":"2026-07-05T06:16:10.836723+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQVPOLWUZHM2WUOE","created_at":"2026-07-05T06:16:10.836723+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQVPOLWU","created_at":"2026-07-05T06:16:10.836723+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/NQVPOLWUZHM2WUOEBMQS54ZBYA","json":"https://pith.science/pith/NQVPOLWUZHM2WUOEBMQS54ZBYA.json","graph_json":"https://pith.science/api/pith-number/NQVPOLWUZHM2WUOEBMQS54ZBYA/graph.json","events_json":"https://pith.science/api/pith-number/NQVPOLWUZHM2WUOEBMQS54ZBYA/events.json","paper":"https://pith.science/paper/NQVPOLWU"},"agent_actions":{"view_html":"https://pith.science/pith/NQVPOLWUZHM2WUOEBMQS54ZBYA","download_json":"https://pith.science/pith/NQVPOLWUZHM2WUOEBMQS54ZBYA.json","view_paper":"https://pith.science/paper/NQVPOLWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.03113&json=true","fetch_graph":"https://pith.science/api/pith-number/NQVPOLWUZHM2WUOEBMQS54ZBYA/graph.json","fetch_events":"https://pith.science/api/pith-number/NQVPOLWUZHM2WUOEBMQS54ZBYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQVPOLWUZHM2WUOEBMQS54ZBYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQVPOLWUZHM2WUOEBMQS54ZBYA/action/storage_attestation","attest_author":"https://pith.science/pith/NQVPOLWUZHM2WUOEBMQS54ZBYA/action/author_attestation","sign_citation":"https://pith.science/pith/NQVPOLWUZHM2WUOEBMQS54ZBYA/action/citation_signature","submit_replication":"https://pith.science/pith/NQVPOLWUZHM2WUOEBMQS54ZBYA/action/replication_record"}},"created_at":"2026-07-05T06:16:10.836723+00:00","updated_at":"2026-07-05T06:16:10.836723+00:00"}