{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7KMPHQDOUYPPUP2OZR3VQ42XWD","short_pith_number":"pith:7KMPHQDO","canonical_record":{"source":{"id":"2502.12853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T13:40:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"54a4ed2e32c4fe6cc4830c8d8db45a2e119bf9d13328aac6e9eeb5ac313de1dc","abstract_canon_sha256":"8ead46da08533a3cbe5e3024f8855dd8611d8f806215bb5b36407c57878f6507"},"schema_version":"1.0"},"canonical_sha256":"fa98f3c06ea61efa3f4ecc77587357b0e63b3e10d0aca2eab71e12610ebd1f7c","source":{"kind":"arxiv","id":"2502.12853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12853","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12853v1","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12853","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"pith_short_12","alias_value":"7KMPHQDOUYPP","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"pith_short_16","alias_value":"7KMPHQDOUYPPUP2O","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"pith_short_8","alias_value":"7KMPHQDO","created_at":"2026-07-05T10:16:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7KMPHQDOUYPPUP2OZR3VQ42XWD","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T13:40:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"54a4ed2e32c4fe6cc4830c8d8db45a2e119bf9d13328aac6e9eeb5ac313de1dc","abstract_canon_sha256":"8ead46da08533a3cbe5e3024f8855dd8611d8f806215bb5b36407c57878f6507"},"schema_version":"1.0"},"canonical_sha256":"fa98f3c06ea61efa3f4ecc77587357b0e63b3e10d0aca2eab71e12610ebd1f7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:25.326660Z","signature_b64":"Ja0Pyy11wg8wW+IEPwNj5JFvUS8POZ6tfKRQ6T9mr90d6vF1plZZ6xSFy/vOwz7kKhsMRZ1yoIbu6uBNNvRUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa98f3c06ea61efa3f4ecc77587357b0e63b3e10d0aca2eab71e12610ebd1f7c","last_reissued_at":"2026-07-05T10:16:25.326099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:25.326099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12853","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKyg8M6/NORHxeehtmZdMGZ5uXHiM3D3Z7C0FQfMJoW15ylH7aq3pvnUzWuM2hXt4s3N+m88YYvoqOe05HnaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:57:00.048374Z"},"content_sha256":"80a4aea639f30eddd47db93beafb1cae356607f2f6dc2eacefea082d906581b1","schema_version":"1.0","event_id":"sha256:80a4aea639f30eddd47db93beafb1cae356607f2f6dc2eacefea082d906581b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7KMPHQDOUYPPUP2OZR3VQ42XWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bang Zhang, Cheng Liu, Jia Li, Jiaqi Chen, Nan Du, Peisong Wang, Ruotian Ma, Xingyan Liu, Xin Zhou","submitted_at":"2025-02-18T13:40:22Z","abstract_excerpt":"Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs' deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains unclear how to improve the thinking abilities of less powerful base models. In this work, we introduce S$^2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Specifically, we first initialize LLMs with iterative self-verification and self-correction behaviors through supervised fine-tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12853","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.12853/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HS70fVdDZMNIXQewEYqzHu6STp+l/qfLCCqCa4BcwVL3vxIowhjmMVNmfB4Jl1tf1cvmC2gDiIEit3PNUwH9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:57:00.049341Z"},"content_sha256":"bb36a7ee6c10d3ae45554fc6324e6d90703933173e5b3ceea3db06ef14d15306","schema_version":"1.0","event_id":"sha256:bb36a7ee6c10d3ae45554fc6324e6d90703933173e5b3ceea3db06ef14d15306"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7KMPHQDOUYPPUP2OZR3VQ42XWD/bundle.json","state_url":"https://pith.science/pith/7KMPHQDOUYPPUP2OZR3VQ42XWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7KMPHQDOUYPPUP2OZR3VQ42XWD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T06:57:00Z","links":{"resolver":"https://pith.science/pith/7KMPHQDOUYPPUP2OZR3VQ42XWD","bundle":"https://pith.science/pith/7KMPHQDOUYPPUP2OZR3VQ42XWD/bundle.json","state":"https://pith.science/pith/7KMPHQDOUYPPUP2OZR3VQ42XWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7KMPHQDOUYPPUP2OZR3VQ42XWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7KMPHQDOUYPPUP2OZR3VQ42XWD","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":"8ead46da08533a3cbe5e3024f8855dd8611d8f806215bb5b36407c57878f6507","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T13:40:22Z","title_canon_sha256":"54a4ed2e32c4fe6cc4830c8d8db45a2e119bf9d13328aac6e9eeb5ac313de1dc"},"schema_version":"1.0","source":{"id":"2502.12853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12853","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12853v1","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12853","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"pith_short_12","alias_value":"7KMPHQDOUYPP","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"pith_short_16","alias_value":"7KMPHQDOUYPPUP2O","created_at":"2026-07-05T10:16:25Z"},{"alias_kind":"pith_short_8","alias_value":"7KMPHQDO","created_at":"2026-07-05T10:16:25Z"}],"graph_snapshots":[{"event_id":"sha256:bb36a7ee6c10d3ae45554fc6324e6d90703933173e5b3ceea3db06ef14d15306","target":"graph","created_at":"2026-07-05T10:16:25Z","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/2502.12853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs' deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains unclear how to improve the thinking abilities of less powerful base models. In this work, we introduce S$^2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Specifically, we first initialize LLMs with iterative self-verification and self-correction behaviors through supervised fine-tu","authors_text":"Bang Zhang, Cheng Liu, Jia Li, Jiaqi Chen, Nan Du, Peisong Wang, Ruotian Ma, Xingyan Liu, Xin Zhou","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T13:40:22Z","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12853","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":"sha256:80a4aea639f30eddd47db93beafb1cae356607f2f6dc2eacefea082d906581b1","target":"record","created_at":"2026-07-05T10:16:25Z","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":"8ead46da08533a3cbe5e3024f8855dd8611d8f806215bb5b36407c57878f6507","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T13:40:22Z","title_canon_sha256":"54a4ed2e32c4fe6cc4830c8d8db45a2e119bf9d13328aac6e9eeb5ac313de1dc"},"schema_version":"1.0","source":{"id":"2502.12853","kind":"arxiv","version":1}},"canonical_sha256":"fa98f3c06ea61efa3f4ecc77587357b0e63b3e10d0aca2eab71e12610ebd1f7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa98f3c06ea61efa3f4ecc77587357b0e63b3e10d0aca2eab71e12610ebd1f7c","first_computed_at":"2026-07-05T10:16:25.326099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:25.326099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ja0Pyy11wg8wW+IEPwNj5JFvUS8POZ6tfKRQ6T9mr90d6vF1plZZ6xSFy/vOwz7kKhsMRZ1yoIbu6uBNNvRUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:25.326660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80a4aea639f30eddd47db93beafb1cae356607f2f6dc2eacefea082d906581b1","sha256:bb36a7ee6c10d3ae45554fc6324e6d90703933173e5b3ceea3db06ef14d15306"],"state_sha256":"d0d9415937512edd939550c3be3da8be2495a04f1ef603a2b74937b3218c8b8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pzPoou6Nsyf7/LoOfv1TW+7Xk7uzVzKOPm4B1rK09W1zgmhYizBIwu4AqS3tHvnNQijo3vkWVFyPt/6CaG+jBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:57:00.055882Z","bundle_sha256":"e37ea122606be88d2be672125ff00fa47680e3185ca7926f99f7408edcbeefae"}}