{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4JNQRESDBMV42FCWIEQ7YW6XB3","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":"b9ddbae7db581a1f8cda5119a81a4557f62659d9f61b46867ae7cb9d25dd19e3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T13:19:11Z","title_canon_sha256":"226d43d5bdc8469474caed7bbd82523dc5183a657d4ace917ebff6ba64fdf485"},"schema_version":"1.0","source":{"id":"2410.09528","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09528","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09528v2","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09528","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_12","alias_value":"4JNQRESDBMV4","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_16","alias_value":"4JNQRESDBMV42FCW","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_8","alias_value":"4JNQRESD","created_at":"2026-07-05T09:25:02Z"}],"graph_snapshots":[{"event_id":"sha256:da5e7e1eb6b04f01fe540836b4cb273f996b758c73a3cd9d7eb658f2769ac444","target":"graph","created_at":"2026-07-05T09:25:02Z","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/2410.09528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Logical reasoning is a crucial task for Large Language Models (LLMs), enabling them to tackle complex problems. Among reasoning tasks, multi-step reasoning poses a particular challenge. Grounded in the theory of formal logic, we have developed an automated method, Multi-step Deduction (MuseD), for deductive reasoning data. MuseD has allowed us to create training and testing datasets for multi-step reasoning. Our generation method enables control over the complexity of the generated instructions, facilitating training and evaluation of models across different difficulty levels. Through RLHF tra","authors_text":"Dong Yan, Jialian Li, Jian Xie, Wei Shen, Yipin Zhang, Yuzi Yan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T13:19:11Z","title":"Boosting Deductive Reasoning with Step Signals In RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09528","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:e899dd03b938e95aef21dfce248a94d2c5e5c817e1ad460621dbf4ad76845072","target":"record","created_at":"2026-07-05T09:25:02Z","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":"b9ddbae7db581a1f8cda5119a81a4557f62659d9f61b46867ae7cb9d25dd19e3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T13:19:11Z","title_canon_sha256":"226d43d5bdc8469474caed7bbd82523dc5183a657d4ace917ebff6ba64fdf485"},"schema_version":"1.0","source":{"id":"2410.09528","kind":"arxiv","version":2}},"canonical_sha256":"e25b0892430b2bcd14564121fc5bd70ee247d4ad6d2ab564dacbee89d37c445b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e25b0892430b2bcd14564121fc5bd70ee247d4ad6d2ab564dacbee89d37c445b","first_computed_at":"2026-07-05T09:25:02.149921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:02.149921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w3QbWvWH5vRT33Lp8I+l+IeVlrwyN4N676/xjikkKQpUtDG0lXvGiHcR0292giGpvwrs8rC0wuauDd3EuddEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:02.150360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09528","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e899dd03b938e95aef21dfce248a94d2c5e5c817e1ad460621dbf4ad76845072","sha256:da5e7e1eb6b04f01fe540836b4cb273f996b758c73a3cd9d7eb658f2769ac444"],"state_sha256":"651e759dcc6ce76d989a392bd101ce32e1757ec59880e38437bba12aacc04666"}