{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TYPEWJFWY5DI6ANOXW2LVATO4G","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":"1e9735d51595535cac91c3b518c33b49eb6186e294442b60944f26bf70665eb7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T20:31:33Z","title_canon_sha256":"9a1ff5b359045aaaa713ad06e265d04278850c9790faffaefc3ce812d6f927e5"},"schema_version":"1.0","source":{"id":"2106.13876","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13876","created_at":"2026-07-05T04:58:00Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13876v4","created_at":"2026-07-05T04:58:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13876","created_at":"2026-07-05T04:58:00Z"},{"alias_kind":"pith_short_12","alias_value":"TYPEWJFWY5DI","created_at":"2026-07-05T04:58:00Z"},{"alias_kind":"pith_short_16","alias_value":"TYPEWJFWY5DI6ANO","created_at":"2026-07-05T04:58:00Z"},{"alias_kind":"pith_short_8","alias_value":"TYPEWJFW","created_at":"2026-07-05T04:58:00Z"}],"graph_snapshots":[{"event_id":"sha256:5178dad2e73282590649db16bf45bf134513ae6885dce7f7bbfd7fb7beee9c23","target":"graph","created_at":"2026-07-05T04:58:00Z","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/2106.13876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view of the features most responsible for a prediction, an NLE allows for a comprehensive description of the decision-making process behind a prediction. However, current models that generate the best extractive rationales or NLEs often fall behind the state-of-the-art (SOTA) in terms of task performance. In this work, we bridge this gap by introducing RExC, a self-rationalizing fram","authors_text":"Bodhisattwa Prasad Majumder, Julian McAuley, Oana-Maria Camburu, Thomas Lukasiewicz","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T20:31:33Z","title":"Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13876","kind":"arxiv","version":4},"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":"sha256:701f24f1764987ee442b3800832e6458bb1e2d522fa9a123b9f81c4ddc98ceb4","target":"record","created_at":"2026-07-05T04:58:00Z","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":"1e9735d51595535cac91c3b518c33b49eb6186e294442b60944f26bf70665eb7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T20:31:33Z","title_canon_sha256":"9a1ff5b359045aaaa713ad06e265d04278850c9790faffaefc3ce812d6f927e5"},"schema_version":"1.0","source":{"id":"2106.13876","kind":"arxiv","version":4}},"canonical_sha256":"9e1e4b24b6c7468f01aebdb4ba826ee1b441f89b3847826301b79bc0f06c0c7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e1e4b24b6c7468f01aebdb4ba826ee1b441f89b3847826301b79bc0f06c0c7a","first_computed_at":"2026-07-05T04:58:00.971805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:00.971805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fuyUg7sKXRiDErWteorJy7epBObgFt6g+lDL5gGR7iuSJvP77tBa2SzXiBfmyPluvY2DCOjXuYdMNjJblHhRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:00.972274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13876","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:701f24f1764987ee442b3800832e6458bb1e2d522fa9a123b9f81c4ddc98ceb4","sha256:5178dad2e73282590649db16bf45bf134513ae6885dce7f7bbfd7fb7beee9c23"],"state_sha256":"8b8560c218959bca6fd5c2b473d269eda1b945fd8cb873247ee8e29e07ffa191"}