{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HSISOVJ37UBHX6TKQ523T4UIQB","short_pith_number":"pith:HSISOVJ3","schema_version":"1.0","canonical_sha256":"3c9127553bfd027bfa6a8775b9f2888053026019d7c5fe4257669df2b72a7463","source":{"kind":"arxiv","id":"1911.03429","version":2},"attestation_state":"computed","paper":{"title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Byron C. Wallace, Caiming Xiong, Eric Lehman, Jay DeYoung, Nazneen Fatema Rajani, Richard Socher, Sarthak Jain","submitted_at":"2019-11-08T18:29:03Z","abstract_excerpt":"State-of-the-art models in NLP are now predominantly based on deep neural networks that are opaque in terms of how they come to make predictions. This limitation has increased interest in designing more interpretable deep models for NLP that reveal the `reasoning' behind model outputs. But work in this direction has been conducted on different datasets and tasks with correspondingly unique aims and metrics; this makes it difficult to track progress. We propose the Evaluating Rationales And Simple English Reasoning (ERASER) benchmark to advance research on interpretable models in NLP. This benc"},"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":"1911.03429","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-08T18:29:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5583463a4e9db8003bbc5f7bc6e8238541997011c0dff8595512dc408277c6ab","abstract_canon_sha256":"ac9c1566cf414317507a55c8d2d64387da2cfd326325904fa58b89a14ab9dd4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:50.737282Z","signature_b64":"CJXdfdDTk0triykCxXf5htuDijOJmmvoXy13RS9tpTsyrfbdjQbJcB/B1Jzt1QA9B9bq3DPSNe5RRLrDsgxDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c9127553bfd027bfa6a8775b9f2888053026019d7c5fe4257669df2b72a7463","last_reissued_at":"2026-07-05T00:57:50.736870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:50.736870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Byron C. Wallace, Caiming Xiong, Eric Lehman, Jay DeYoung, Nazneen Fatema Rajani, Richard Socher, Sarthak Jain","submitted_at":"2019-11-08T18:29:03Z","abstract_excerpt":"State-of-the-art models in NLP are now predominantly based on deep neural networks that are opaque in terms of how they come to make predictions. This limitation has increased interest in designing more interpretable deep models for NLP that reveal the `reasoning' behind model outputs. But work in this direction has been conducted on different datasets and tasks with correspondingly unique aims and metrics; this makes it difficult to track progress. We propose the Evaluating Rationales And Simple English Reasoning (ERASER) benchmark to advance research on interpretable models in NLP. This benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03429","kind":"arxiv","version":2},"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/1911.03429/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":"1911.03429","created_at":"2026-07-05T00:57:50.736932+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.03429v2","created_at":"2026-07-05T00:57:50.736932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03429","created_at":"2026-07-05T00:57:50.736932+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSISOVJ37UBH","created_at":"2026-07-05T00:57:50.736932+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSISOVJ37UBHX6TK","created_at":"2026-07-05T00:57:50.736932+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSISOVJ3","created_at":"2026-07-05T00:57:50.736932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07604","citing_title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07604","citing_title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2210.15304","citing_title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16608","citing_title":"Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11161","citing_title":"Interpretability Can Be Actionable","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB","json":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB.json","graph_json":"https://pith.science/api/pith-number/HSISOVJ37UBHX6TKQ523T4UIQB/graph.json","events_json":"https://pith.science/api/pith-number/HSISOVJ37UBHX6TKQ523T4UIQB/events.json","paper":"https://pith.science/paper/HSISOVJ3"},"agent_actions":{"view_html":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB","download_json":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB.json","view_paper":"https://pith.science/paper/HSISOVJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.03429&json=true","fetch_graph":"https://pith.science/api/pith-number/HSISOVJ37UBHX6TKQ523T4UIQB/graph.json","fetch_events":"https://pith.science/api/pith-number/HSISOVJ37UBHX6TKQ523T4UIQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB/action/storage_attestation","attest_author":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB/action/author_attestation","sign_citation":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB/action/citation_signature","submit_replication":"https://pith.science/pith/HSISOVJ37UBHX6TKQ523T4UIQB/action/replication_record"}},"created_at":"2026-07-05T00:57:50.736932+00:00","updated_at":"2026-07-05T00:57:50.736932+00:00"}