{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UXH5OU23URAK47NS4YEKZKUV3M","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":"26a6b4d50d74ded879b14f18e9c5f6c55f1c50e312ea2c222a545dd937ca729d","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-09T18:00:04Z","title_canon_sha256":"14970146174806336930a7bb9ff4953b69065b1e851f4670be80aae1cc31df8d"},"schema_version":"1.0","source":{"id":"2010.04736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04736","created_at":"2026-07-05T01:41:58Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04736v1","created_at":"2026-07-05T01:41:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04736","created_at":"2026-07-05T01:41:58Z"},{"alias_kind":"pith_short_12","alias_value":"UXH5OU23URAK","created_at":"2026-07-05T01:41:58Z"},{"alias_kind":"pith_short_16","alias_value":"UXH5OU23URAK47NS","created_at":"2026-07-05T01:41:58Z"},{"alias_kind":"pith_short_8","alias_value":"UXH5OU23","created_at":"2026-07-05T01:41:58Z"}],"graph_snapshots":[{"event_id":"sha256:0fcc5e93406159fce8b6c1ca21d124c42bcbe3bbf30af63e80c58eb6e29af4d1","target":"graph","created_at":"2026-07-05T01:41:58Z","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/2010.04736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Two main approaches for evaluating the quality of machine-generated rationales are: 1) using human rationales as a gold standard; and 2) automated metrics based on how rationales affect model behavior. An open question, however, is how human rationales fare with these automatic metrics. Analyzing a variety of datasets and models, we find that human rationales do not necessarily perform well on these metrics. To unpack this finding, we propose improved metrics to account for model-dependent baseline performance. We then propose two methods to further characterize rationale quality, one based on","authors_text":"Anirudh Rathore, Chenhao Tan, Samuel Carton","cross_cats":["cs.AI","cs.CY","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-09T18:00:04Z","title":"Evaluating and Characterizing Human Rationales"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04736","kind":"arxiv","version":1},"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":"sha256:8e218b285d9243b5d462431d5125783d2421175e5dce8c4d32c520a2d1554bd7","target":"record","created_at":"2026-07-05T01:41:58Z","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":"26a6b4d50d74ded879b14f18e9c5f6c55f1c50e312ea2c222a545dd937ca729d","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-09T18:00:04Z","title_canon_sha256":"14970146174806336930a7bb9ff4953b69065b1e851f4670be80aae1cc31df8d"},"schema_version":"1.0","source":{"id":"2010.04736","kind":"arxiv","version":1}},"canonical_sha256":"a5cfd7535ba440ae7db2e608acaa95db1fb66e471a18e45da05a7a4b192abdf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5cfd7535ba440ae7db2e608acaa95db1fb66e471a18e45da05a7a4b192abdf1","first_computed_at":"2026-07-05T01:41:58.655005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:58.655005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJ+hRqnsrC8brbpvaYBHf5qxdIh0HlayD3DeQ+OnYcOtqEX+QkEcXTAcXXmfBSvK8/WOunNpgQhrIJ43jOCPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:58.655499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e218b285d9243b5d462431d5125783d2421175e5dce8c4d32c520a2d1554bd7","sha256:0fcc5e93406159fce8b6c1ca21d124c42bcbe3bbf30af63e80c58eb6e29af4d1"],"state_sha256":"ea757874a06332dd87e792a0e871f027f9e3d76e51a497e6e950c0a4acfe33c2"}