{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C7TLIRVABBQMXUKSVUB3DTN23F","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":"e5e46181d6cd21a9b5b905b95d6407339c451ba2c82554c9ac9ec221d9561c20","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T08:52:13Z","title_canon_sha256":"52f4ae38c7e0091c5499209d627e8e6fbbbf2df76bb0830ac7775befb82a3112"},"schema_version":"1.0","source":{"id":"2310.05074","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05074","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05074v3","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05074","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"C7TLIRVABBQM","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"C7TLIRVABBQMXUKS","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"C7TLIRVA","created_at":"2026-07-05T07:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:2f23f8f3b3066d0362f7abd5252539767e20f9bfc3bd9d6e09ccd138bf558e8f","target":"graph","created_at":"2026-07-05T07:03:31Z","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/2310.05074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-Thought (CoT) prompting has proven to be effective in enhancing the reasoning capabilities of Large Language Models (LLMs) with at least 100 billion parameters. However, it is ineffective or even detrimental when applied to reasoning tasks in Smaller Language Models (SLMs) with less than 10 billion parameters. To address this limitation, we introduce Dialogue-guided Chain-of-Thought (DialCoT) which employs a dialogue format to generate intermediate reasoning steps, guiding the model toward the final answer. Additionally, we optimize the model's reasoning path selection using the Proxi","authors_text":"Baoyuan Wang, Chengcheng Han, Che Zhang, Ming Gao, Xiang Li, Xiaowei Du, Yixin Lian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T08:52:13Z","title":"DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05074","kind":"arxiv","version":3},"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":"sha256:3257131d5054a7716b534cd5d983072ca0b5a0814397a38c7830f52c822da85b","target":"record","created_at":"2026-07-05T07:03:31Z","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":"e5e46181d6cd21a9b5b905b95d6407339c451ba2c82554c9ac9ec221d9561c20","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T08:52:13Z","title_canon_sha256":"52f4ae38c7e0091c5499209d627e8e6fbbbf2df76bb0830ac7775befb82a3112"},"schema_version":"1.0","source":{"id":"2310.05074","kind":"arxiv","version":3}},"canonical_sha256":"17e6b446a00860cbd152ad03b1cdbad968706828b7dd35eafda16f701c4abea9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17e6b446a00860cbd152ad03b1cdbad968706828b7dd35eafda16f701c4abea9","first_computed_at":"2026-07-05T07:03:31.882167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:31.882167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aS7jMPMQy3cU1Mn7+X6W4tDkspuMfzfS4JAqHlzmOxWTdBfYIPTbooYp/D3YhU0jV/q4bXtdnq0D47qVGySuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:31.882669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05074","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3257131d5054a7716b534cd5d983072ca0b5a0814397a38c7830f52c822da85b","sha256:2f23f8f3b3066d0362f7abd5252539767e20f9bfc3bd9d6e09ccd138bf558e8f"],"state_sha256":"1e5d2aa1ece41d3314e6b2fbfb20128e3e0488bb664f549ba9366449f31aea91"}