{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E3DKONIUMUFOI5K55YMTB2M6QY","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":"e277f35080c36e41280bc9424377eaccd66a35e1fff39a011ae94a4b8b34428b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T14:05:04Z","title_canon_sha256":"79bd6ed15ade975468c1b1d2959118d24e0d4cf238f5712845067ab5149c1473"},"schema_version":"1.0","source":{"id":"2412.08393","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08393","created_at":"2026-07-05T09:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08393v1","created_at":"2026-07-05T09:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08393","created_at":"2026-07-05T09:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"E3DKONIUMUFO","created_at":"2026-07-05T09:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"E3DKONIUMUFOI5K5","created_at":"2026-07-05T09:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"E3DKONIU","created_at":"2026-07-05T09:47:49Z"}],"graph_snapshots":[{"event_id":"sha256:b73afa92e94a70246532e5d4363979cc35ec4629ce631c7a1b7e54d1bc822583","target":"graph","created_at":"2026-07-05T09:47:49Z","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/2412.08393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as supervised fine-tuning and distillation, often depend on costly external signals, resulting in SLMs being overly confident with limited supervision signals, thus limiting their abilities. Therefore, this study enables SLMs to learn to reason from self-iterative feedback. By combining odds ratio preference optimization (ORPO), we fine-tune and align SLMs using posi","authors_text":"Jin Wang, Kaiyuan Chen, Xuejie Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T14:05:04Z","title":"Learning to Reason via Self-Iterative Process Feedback for Small Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08393","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:e8640f188f70a2b76c3d2e3e748e35d6c84259c25da87e0a47784655a158dc1e","target":"record","created_at":"2026-07-05T09:47:49Z","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":"e277f35080c36e41280bc9424377eaccd66a35e1fff39a011ae94a4b8b34428b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T14:05:04Z","title_canon_sha256":"79bd6ed15ade975468c1b1d2959118d24e0d4cf238f5712845067ab5149c1473"},"schema_version":"1.0","source":{"id":"2412.08393","kind":"arxiv","version":1}},"canonical_sha256":"26c6a73514650ae4755dee1930e99e860efa19d14a90087a025b29672e993249","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26c6a73514650ae4755dee1930e99e860efa19d14a90087a025b29672e993249","first_computed_at":"2026-07-05T09:47:49.356292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:49.356292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kpfILQ7lGw55MGVoKIsfS8RKz7u1Cwddh7Gh0rNBBMfMxaeXG2xTVjyPyxRP3GTaYQHnFGNidgoUPns504irBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:49.356770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08393","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8640f188f70a2b76c3d2e3e748e35d6c84259c25da87e0a47784655a158dc1e","sha256:b73afa92e94a70246532e5d4363979cc35ec4629ce631c7a1b7e54d1bc822583"],"state_sha256":"d74df8f39975ae38cd5376f685364bbdddcda26d2b754c84ea982038e4a6981b"}