{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VTYMM4MIPE7Q3QTSNTAG64SVVG","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":"cc009e85fe56f8b9cdd875d13f1eb35586c425d49907e9a08d64bf41ab3268b5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:33:30Z","title_canon_sha256":"eebaeb2a3e475dc352715434ccf1eceb508ca548ffc72603c41b96d7166ea9f9"},"schema_version":"1.0","source":{"id":"2410.03767","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03767","created_at":"2026-07-05T10:31:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03767v2","created_at":"2026-07-05T10:31:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03767","created_at":"2026-07-05T10:31:47Z"},{"alias_kind":"pith_short_12","alias_value":"VTYMM4MIPE7Q","created_at":"2026-07-05T10:31:47Z"},{"alias_kind":"pith_short_16","alias_value":"VTYMM4MIPE7Q3QTS","created_at":"2026-07-05T10:31:47Z"},{"alias_kind":"pith_short_8","alias_value":"VTYMM4MI","created_at":"2026-07-05T10:31:47Z"}],"graph_snapshots":[{"event_id":"sha256:27f67ae6bb1fe7539fe32c60a993e44fa7f01e86295bef10d395a1778c73d2d3","target":"graph","created_at":"2026-07-05T10:31:47Z","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/2410.03767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first derive novel metrics that balance accuracy in factual and counterfactual questions, capturing a more complete view of the reasoning abilities of language models than traditional factual-only based metrics. Second, we propose several fine-tuning approaches that aim to elicit better reasoning mechanisms, in the sense of the proposed metrics. Finally, we evaluat","authors_text":"Aditya V. Nori, Alihan H\\\"uy\\\"uk, Jacqueline Maasch, Javier Gonz\\'alez, Xinnuo Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:33:30Z","title":"Reasoning Elicitation in Language Models via Counterfactual Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03767","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":"sha256:8898c7966534680898f706ebd6a01d5b28fea3df1f75210e7b6cd6a81ac8b986","target":"record","created_at":"2026-07-05T10:31:47Z","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":"cc009e85fe56f8b9cdd875d13f1eb35586c425d49907e9a08d64bf41ab3268b5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:33:30Z","title_canon_sha256":"eebaeb2a3e475dc352715434ccf1eceb508ca548ffc72603c41b96d7166ea9f9"},"schema_version":"1.0","source":{"id":"2410.03767","kind":"arxiv","version":2}},"canonical_sha256":"acf0c67188793f0dc2726cc06f7255a99bd3d4b209f17fd1ab1643ef09425c22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acf0c67188793f0dc2726cc06f7255a99bd3d4b209f17fd1ab1643ef09425c22","first_computed_at":"2026-07-05T10:31:47.690017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:47.690017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ejcjt/VaoGOrr9YsI7e6MUy7MVahWlzo9f3V7SSR3tkSWFblqK9lbP8Uj2JxOjd9ayaMxXxEZEa6jutM0WIVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:47.690563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03767","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8898c7966534680898f706ebd6a01d5b28fea3df1f75210e7b6cd6a81ac8b986","sha256:27f67ae6bb1fe7539fe32c60a993e44fa7f01e86295bef10d395a1778c73d2d3"],"state_sha256":"af9d95ff61724066440f22d4f322c015b539ca38291cec8fcf7b5596736ec482"}