{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GSMMPZN7R2IDES2DRE7LHPW4ES","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":"f655fccc985e006982655c2a45ff2e954541f186acf7a28bb78544ffdeddd215","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-05T11:32:48Z","title_canon_sha256":"836b32aa75966294ed298028bd0ea4ed4de11465ef3db8de4a867b068bdb5e0b"},"schema_version":"1.0","source":{"id":"2309.02144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02144","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02144v1","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02144","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"GSMMPZN7R2ID","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"GSMMPZN7R2IDES2D","created_at":"2026-07-05T06:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"GSMMPZN7","created_at":"2026-07-05T06:47:49Z"}],"graph_snapshots":[{"event_id":"sha256:7109f68fee45ab7d07d30f370a432fc29fe512399d85c3ab2f098df972175de4","target":"graph","created_at":"2026-07-05T06:47:49Z","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/2309.02144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal that fine-tuning LLMs on data with the chain of thought (COT) reasoning process can significantly enhance their reasoning capabilities. However, we find that the fine-tuned LLMs suffer from an \\textit{Assessment Misalignment} problem, i.e., they frequently assign higher scores to subpar COTs, leading to potential limitations in their reasoning abilities. To","authors_text":"Binghuai Lin, Feifan Song, Lei Li, Liang Chen, Peiyi Wang, Tianyu Liu, Yunbo Cao, Zhifang Sui","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-05T11:32:48Z","title":"Making Large Language Models Better Reasoners with Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02144","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":"sha256:90a58cbb53e322d15816966c9d519336b7c9098a02e6f0a9f6402b5c4cf75c76","target":"record","created_at":"2026-07-05T06:47:49Z","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":"f655fccc985e006982655c2a45ff2e954541f186acf7a28bb78544ffdeddd215","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-05T11:32:48Z","title_canon_sha256":"836b32aa75966294ed298028bd0ea4ed4de11465ef3db8de4a867b068bdb5e0b"},"schema_version":"1.0","source":{"id":"2309.02144","kind":"arxiv","version":1}},"canonical_sha256":"3498c7e5bf8e90324b43893eb3bedc248be7cf3ec73f7d1f88d42e1bf55172da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3498c7e5bf8e90324b43893eb3bedc248be7cf3ec73f7d1f88d42e1bf55172da","first_computed_at":"2026-07-05T06:47:49.048630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:49.048630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qL2MFVPEuN789nWGx0rj4R0PZX0FUJgdxnBFgkg0wSeo+NbjJum7JfPvqQVrlYrXncBiZ6bEHA3MVE2ywIFKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:49.049133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90a58cbb53e322d15816966c9d519336b7c9098a02e6f0a9f6402b5c4cf75c76","sha256:7109f68fee45ab7d07d30f370a432fc29fe512399d85c3ab2f098df972175de4"],"state_sha256":"f97786397f92151bc6bb20e58260f6556021e45198b1fed55a4897ff13e978fe"}