{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TJZ4JGL6HXKFTLXJGUORKR7KOC","short_pith_number":"pith:TJZ4JGL6","schema_version":"1.0","canonical_sha256":"9a73c4997e3dd459aee9351d1547ea7080bad15a588494670709116fc0d85663","source":{"kind":"arxiv","id":"2205.12254","version":1},"attestation_state":"computed","paper":{"title":"Interpretation Quality Score for Measuring the Quality of interpretability methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Saeed Hassanpour, Sean Xie, Soroush Vosoughi","submitted_at":"2022-05-24T17:57:55Z","abstract_excerpt":"Machine learning (ML) models have been applied to a wide range of natural language processing (NLP) tasks in recent years. In addition to making accurate decisions, the necessity of understanding how models make their decisions has become apparent in many applications. To that end, many interpretability methods that help explain the decision processes of ML models have been developed. Yet, there currently exists no widely-accepted metric to evaluate the quality of explanations generated by these methods. As a result, there currently is no standard way of measuring to what degree an interpretab"},"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":"2205.12254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T17:57:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fd61e920441c1c4a06012a1a46cef81659deae6d03a2a13ebb5079576678e6e9","abstract_canon_sha256":"7d1fb430eaddc865cc5f0262db1e2a3eb0914724504efa5b6101f0617193ed36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:51.374200Z","signature_b64":"DrVwoTV5cWmGCAlT5PgHpvTH1eRaww2VEjTRoKSUPZWzak2i7cNDVy8MHNd3JmIZqN7QZj1RLV5Ku/EwRw5tBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a73c4997e3dd459aee9351d1547ea7080bad15a588494670709116fc0d85663","last_reissued_at":"2026-07-05T07:07:51.373781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:51.373781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretation Quality Score for Measuring the Quality of interpretability methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Saeed Hassanpour, Sean Xie, Soroush Vosoughi","submitted_at":"2022-05-24T17:57:55Z","abstract_excerpt":"Machine learning (ML) models have been applied to a wide range of natural language processing (NLP) tasks in recent years. In addition to making accurate decisions, the necessity of understanding how models make their decisions has become apparent in many applications. To that end, many interpretability methods that help explain the decision processes of ML models have been developed. Yet, there currently exists no widely-accepted metric to evaluate the quality of explanations generated by these methods. As a result, there currently is no standard way of measuring to what degree an interpretab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12254","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/2205.12254/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":"2205.12254","created_at":"2026-07-05T07:07:51.373842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12254v1","created_at":"2026-07-05T07:07:51.373842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12254","created_at":"2026-07-05T07:07:51.373842+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJZ4JGL6HXKF","created_at":"2026-07-05T07:07:51.373842+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJZ4JGL6HXKFTLXJ","created_at":"2026-07-05T07:07:51.373842+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJZ4JGL6","created_at":"2026-07-05T07:07:51.373842+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16056","citing_title":"Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainability","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC","json":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC.json","graph_json":"https://pith.science/api/pith-number/TJZ4JGL6HXKFTLXJGUORKR7KOC/graph.json","events_json":"https://pith.science/api/pith-number/TJZ4JGL6HXKFTLXJGUORKR7KOC/events.json","paper":"https://pith.science/paper/TJZ4JGL6"},"agent_actions":{"view_html":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC","download_json":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC.json","view_paper":"https://pith.science/paper/TJZ4JGL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12254&json=true","fetch_graph":"https://pith.science/api/pith-number/TJZ4JGL6HXKFTLXJGUORKR7KOC/graph.json","fetch_events":"https://pith.science/api/pith-number/TJZ4JGL6HXKFTLXJGUORKR7KOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC/action/storage_attestation","attest_author":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC/action/author_attestation","sign_citation":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC/action/citation_signature","submit_replication":"https://pith.science/pith/TJZ4JGL6HXKFTLXJGUORKR7KOC/action/replication_record"}},"created_at":"2026-07-05T07:07:51.373842+00:00","updated_at":"2026-07-05T07:07:51.373842+00:00"}