{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QQLXAFHYTAH62H2AJ7CDPN5BGR","short_pith_number":"pith:QQLXAFHY","schema_version":"1.0","canonical_sha256":"84177014f8980fed1f404fc437b7a1346e18f7a7fdd9e6c328be548bc796c417","source":{"kind":"arxiv","id":"2503.07914","version":1},"attestation_state":"computed","paper":{"title":"Demystifying the Accuracy-Interpretability Trade-Off: A Case Study of Inferring Ratings from Reviews","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Michael P. Brundage, Min Wu, Pranjal Atrey, Sanghamitra Dutta","submitted_at":"2025-03-10T23:17:46Z","abstract_excerpt":"Interpretable machine learning models offer understandable reasoning behind their decision-making process, though they may not always match the performance of their black-box counterparts. This trade-off between interpretability and model performance has sparked discussions around the deployment of AI, particularly in critical applications where knowing the rationale of decision-making is essential for trust and accountability. In this study, we conduct a comparative analysis of several black-box and interpretable models, focusing on a specific NLP use case that has received limited attention:"},"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":"2503.07914","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-10T23:17:46Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a04aa7712252ce8558258326d85184c7d948965daf7a45c048fb1b23cfa9a1ca","abstract_canon_sha256":"96a17aa2c7a75c725a233cac6b62a9e5d0013c5c82710774ee01e81b25e7d89f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:46.550298Z","signature_b64":"fJ/wsHI7V9YsVn0CT/xXZ2e4xwlEmoctAP4kCJOWnm4xoV8KlCKccm6RtIowN5Vu6stG5GTjgZPzDFu1U3k+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84177014f8980fed1f404fc437b7a1346e18f7a7fdd9e6c328be548bc796c417","last_reissued_at":"2026-07-05T10:28:46.549333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:46.549333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Demystifying the Accuracy-Interpretability Trade-Off: A Case Study of Inferring Ratings from Reviews","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Michael P. Brundage, Min Wu, Pranjal Atrey, Sanghamitra Dutta","submitted_at":"2025-03-10T23:17:46Z","abstract_excerpt":"Interpretable machine learning models offer understandable reasoning behind their decision-making process, though they may not always match the performance of their black-box counterparts. This trade-off between interpretability and model performance has sparked discussions around the deployment of AI, particularly in critical applications where knowing the rationale of decision-making is essential for trust and accountability. In this study, we conduct a comparative analysis of several black-box and interpretable models, focusing on a specific NLP use case that has received limited attention:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07914","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/2503.07914/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":"2503.07914","created_at":"2026-07-05T10:28:46.549483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07914v1","created_at":"2026-07-05T10:28:46.549483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07914","created_at":"2026-07-05T10:28:46.549483+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQLXAFHYTAH6","created_at":"2026-07-05T10:28:46.549483+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQLXAFHYTAH62H2A","created_at":"2026-07-05T10:28:46.549483+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQLXAFHY","created_at":"2026-07-05T10:28:46.549483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.19770","citing_title":"The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR","json":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR.json","graph_json":"https://pith.science/api/pith-number/QQLXAFHYTAH62H2AJ7CDPN5BGR/graph.json","events_json":"https://pith.science/api/pith-number/QQLXAFHYTAH62H2AJ7CDPN5BGR/events.json","paper":"https://pith.science/paper/QQLXAFHY"},"agent_actions":{"view_html":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR","download_json":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR.json","view_paper":"https://pith.science/paper/QQLXAFHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07914&json=true","fetch_graph":"https://pith.science/api/pith-number/QQLXAFHYTAH62H2AJ7CDPN5BGR/graph.json","fetch_events":"https://pith.science/api/pith-number/QQLXAFHYTAH62H2AJ7CDPN5BGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR/action/storage_attestation","attest_author":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR/action/author_attestation","sign_citation":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR/action/citation_signature","submit_replication":"https://pith.science/pith/QQLXAFHYTAH62H2AJ7CDPN5BGR/action/replication_record"}},"created_at":"2026-07-05T10:28:46.549483+00:00","updated_at":"2026-07-05T10:28:46.549483+00:00"}