{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GWRLFIWRUDKIHHFRT5N2C6NY54","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"427239ce76107967a9b989ab83102881c8945384f7e46bfdba98f29e450cfcd8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T19:31:50Z","title_canon_sha256":"6cbcd713f6c81c368c26644b73bbad7d9f31874eb637b5ffcb81abc38d41e4eb"},"schema_version":"1.0","source":{"id":"2305.03117","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03117","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03117v2","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03117","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"GWRLFIWRUDKI","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"GWRLFIWRUDKIHHFR","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"GWRLFIWR","created_at":"2026-07-05T06:12:02Z"}],"graph_snapshots":[{"event_id":"sha256:29e959c4526f453dfee34febd46a3256a455b6593658b46ae441dd9371e35fea","target":"graph","created_at":"2026-07-05T06:12:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.03117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human-annotated labels and explanations are critical for training explainable NLP models. However, unlike human-annotated labels whose quality is easier to calibrate (e.g., with a majority vote), human-crafted free-form explanations can be quite subjective. Before blindly using them as ground truth to train ML models, a vital question needs to be asked: How do we evaluate a human-annotated explanation's quality? In this paper, we build on the view that the quality of a human-annotated explanation can be measured based on its helpfulness (or impairment) to the ML models' performance for the des","authors_text":"Bingsheng Yao, Dakuo Wang, James Hendler, Lucian Popa, Prithviraj Sen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T19:31:50Z","title":"Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03117","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:08053fe20ad47f70daca042fb2513c1b2e90bac067f68101a299742e43810a83","target":"record","created_at":"2026-07-05T06:12:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"427239ce76107967a9b989ab83102881c8945384f7e46bfdba98f29e450cfcd8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T19:31:50Z","title_canon_sha256":"6cbcd713f6c81c368c26644b73bbad7d9f31874eb637b5ffcb81abc38d41e4eb"},"schema_version":"1.0","source":{"id":"2305.03117","kind":"arxiv","version":2}},"canonical_sha256":"35a2b2a2d1a0d4839cb19f5ba179b8ef06b9badf7342438cbbba841ad7692d5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35a2b2a2d1a0d4839cb19f5ba179b8ef06b9badf7342438cbbba841ad7692d5c","first_computed_at":"2026-07-05T06:12:02.375518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:02.375518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v9TtfobpUlGPg/rwWjmfoKmT65kD3gMLy3VrErRlANGyRy7rUXzV1+WgbWXEWan9DVkBf4O5B3cOHM/OaI1bDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:02.375887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03117","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08053fe20ad47f70daca042fb2513c1b2e90bac067f68101a299742e43810a83","sha256:29e959c4526f453dfee34febd46a3256a455b6593658b46ae441dd9371e35fea"],"state_sha256":"e4a65bb85f7b11e7e1b1bc2bf78729cab8622cc3677b57322d7c01f6b343d668"}