{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LUUT4VXKPRGLBKHHFYFMXECY6C","short_pith_number":"pith:LUUT4VXK","schema_version":"1.0","canonical_sha256":"5d293e56ea7c4cb0a8e72e0acb9058f0b846c409d5f290d9903f8039f8c93c81","source":{"kind":"arxiv","id":"2205.04559","version":1},"attestation_state":"computed","paper":{"title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ana Lucic, Maurits Bleeker, Michael Neely, Stefan F. Schouten","submitted_at":"2022-05-09T21:07:39Z","abstract_excerpt":"There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of \"attention as explanation\" has so far been evaluated by computing the rank correlation between attention-based explanations and existing feature attribution explanations using LSTM-based models. In our work, we (i) compare the rank correlation between five more recent feature attribution methods and two attention-based methods, on two types of NLP tasks, and (ii) "},"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":"2205.04559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-09T21:07:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"af0316d8931592310e20332b2f667ea13ca0936e378105a377c6909af73bca8d","abstract_canon_sha256":"e2492b1c544714a4aaf6c70e5a10261e7d7a76c4620ccde175b16d05d9ae0c69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:37.640090Z","signature_b64":"3X6I8r5EWV0L9dQPY9JVFDsYY5nB6oUnnSkU3BmDfh6ei6J2HmVqMLZo30p+hRJjgaxiwdng+9y4xG7VV7Y8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d293e56ea7c4cb0a8e72e0acb9058f0b846c409d5f290d9903f8039f8c93c81","last_reissued_at":"2026-07-05T04:21:37.639674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:37.639674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ana Lucic, Maurits Bleeker, Michael Neely, Stefan F. Schouten","submitted_at":"2022-05-09T21:07:39Z","abstract_excerpt":"There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of \"attention as explanation\" has so far been evaluated by computing the rank correlation between attention-based explanations and existing feature attribution explanations using LSTM-based models. In our work, we (i) compare the rank correlation between five more recent feature attribution methods and two attention-based methods, on two types of NLP tasks, and (ii) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04559","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/2205.04559/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":"2205.04559","created_at":"2026-07-05T04:21:37.639734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.04559v1","created_at":"2026-07-05T04:21:37.639734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04559","created_at":"2026-07-05T04:21:37.639734+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUUT4VXKPRGL","created_at":"2026-07-05T04:21:37.639734+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUUT4VXKPRGLBKHH","created_at":"2026-07-05T04:21:37.639734+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUUT4VXK","created_at":"2026-07-05T04:21:37.639734+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/LUUT4VXKPRGLBKHHFYFMXECY6C","json":"https://pith.science/pith/LUUT4VXKPRGLBKHHFYFMXECY6C.json","graph_json":"https://pith.science/api/pith-number/LUUT4VXKPRGLBKHHFYFMXECY6C/graph.json","events_json":"https://pith.science/api/pith-number/LUUT4VXKPRGLBKHHFYFMXECY6C/events.json","paper":"https://pith.science/paper/LUUT4VXK"},"agent_actions":{"view_html":"https://pith.science/pith/LUUT4VXKPRGLBKHHFYFMXECY6C","download_json":"https://pith.science/pith/LUUT4VXKPRGLBKHHFYFMXECY6C.json","view_paper":"https://pith.science/paper/LUUT4VXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.04559&json=true","fetch_graph":"https://pith.science/api/pith-number/LUUT4VXKPRGLBKHHFYFMXECY6C/graph.json","fetch_events":"https://pith.science/api/pith-number/LUUT4VXKPRGLBKHHFYFMXECY6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUUT4VXKPRGLBKHHFYFMXECY6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUUT4VXKPRGLBKHHFYFMXECY6C/action/storage_attestation","attest_author":"https://pith.science/pith/LUUT4VXKPRGLBKHHFYFMXECY6C/action/author_attestation","sign_citation":"https://pith.science/pith/LUUT4VXKPRGLBKHHFYFMXECY6C/action/citation_signature","submit_replication":"https://pith.science/pith/LUUT4VXKPRGLBKHHFYFMXECY6C/action/replication_record"}},"created_at":"2026-07-05T04:21:37.639734+00:00","updated_at":"2026-07-05T04:21:37.639734+00:00"}