{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WE6ONQ4VWP4JBDXVC7YOYNV5SF","short_pith_number":"pith:WE6ONQ4V","schema_version":"1.0","canonical_sha256":"b13ce6c395b3f8908ef517f0ec36bd9178cc3a3844be93dfdc059ab8275b4f73","source":{"kind":"arxiv","id":"2605.12400","version":2},"attestation_state":"computed","paper":{"title":"OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Outcome-guided logit steering calibrates teacher responses in on-policy self-distillation by contrasting successful and failed trajectories, reducing reflection bias for better LLM reasoning.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Weitong Zhang, Xiaoyun Wang, Yuxiao Yang","submitted_at":"2026-05-12T17:00:53Z","abstract_excerpt":"We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite its promise, OPSD can suffer from training instability due to a pattern mismatch between teacher and student responses. Self-reflected teacher responses may introduce reflection-induced biases and response templates that miscalibrate token-level supervision, ultimately harming the student's reasoning ability. To mitigate this issue, we propose OGLS-SD, an outcome-guided logit-steering framework that lever"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:00:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4496316516826098f6407c5ab502ca827ecb01db1d825e03d18de392fd5ba39f","abstract_canon_sha256":"a8c9c992aed92afea13155de0dc839558215e5b084a3f35b61b942ac9967fdda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:48.438591Z","signature_b64":"qV1on+NiRFbGZvUYk437cpA2wmgN+5OUpowBpfvVVeSf0C2Hc5iYKHgP5y7E5jFkEujP45oWjvXluHvYDu+VDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b13ce6c395b3f8908ef517f0ec36bd9178cc3a3844be93dfdc059ab8275b4f73","last_reissued_at":"2026-06-02T01:03:48.438082Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:48.438082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Outcome-guided logit steering calibrates teacher responses in on-policy self-distillation by contrasting successful and failed trajectories, reducing reflection bias for better LLM reasoning.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Weitong Zhang, Xiaoyun Wang, Yuxiao Yang","submitted_at":"2026-05-12T17:00:53Z","abstract_excerpt":"We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite its promise, OPSD can suffer from training instability due to a pattern mismatch between teacher and student responses. Self-reflected teacher responses may introduce reflection-induced biases and response templates that miscalibrate token-level supervision, ultimately harming the student's reasoning ability. To mitigate this issue, we propose OGLS-SD, an outcome-guided logit-steering framework that lever"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By combining outcome-level correctness with dense token-level guidance through logit steering, OGLS-SD stabilizes self-distillation and improves reasoning performance over standard OPSD and other variants across diverse benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That verifiable outcome rewards can reliably contrast successful and failed on-policy trajectories to calibrate teacher logits and mitigate reflection-induced bias without introducing new calibration issues or depending on tasks where outcomes are easily verifiable.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OGLS-SD improves LLM reasoning by using verifiable outcome rewards to guide logit steering that calibrates teacher distributions in on-policy self-distillation, addressing reflection-induced mismatches.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Outcome-guided logit steering calibrates teacher responses in on-policy self-distillation by contrasting successful and failed trajectories, reducing reflection bias for better LLM reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a34ed2143aab1182847d78b1fc606f13e67ee4443a9575f7535b78c8165d112d"},"source":{"id":"2605.12400","kind":"arxiv","version":2},"verdict":{"id":"3c816f6c-41af-4df3-8077-fa5a10a1946d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T05:14:01.558810Z","strongest_claim":"By combining outcome-level correctness with dense token-level guidance through logit steering, OGLS-SD stabilizes self-distillation and improves reasoning performance over standard OPSD and other variants across diverse benchmarks.","one_line_summary":"OGLS-SD improves LLM reasoning by using verifiable outcome rewards to guide logit steering that calibrates teacher distributions in on-policy self-distillation, addressing reflection-induced mismatches.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That verifiable outcome rewards can reliably contrast successful and failed on-policy trajectories to calibrate teacher logits and mitigate reflection-induced bias without introducing new calibration issues or depending on tasks where outcomes are easily verifiable.","pith_extraction_headline":"Outcome-guided logit steering calibrates teacher responses in on-policy self-distillation by contrasting successful and failed trajectories, reducing reflection bias for better LLM reasoning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.12400/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-26T14:40:00.497927Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T13:31:24.992235Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T09:37:46.618193Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.872449Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4ccc60c6e5dbd90b21ad39be1748bbd4cf3e8a42ec904c34d6b7d211b50113cc"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bd398c76ef47e7aeaca8a0939b173d541fae73171e53f59e79da53c3bf777d43"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.12400","created_at":"2026-06-02T01:03:48.438154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12400v2","created_at":"2026-06-02T01:03:48.438154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12400","created_at":"2026-06-02T01:03:48.438154+00:00"},{"alias_kind":"pith_short_12","alias_value":"WE6ONQ4VWP4J","created_at":"2026-06-02T01:03:48.438154+00:00"},{"alias_kind":"pith_short_16","alias_value":"WE6ONQ4VWP4JBDXV","created_at":"2026-06-02T01:03:48.438154+00:00"},{"alias_kind":"pith_short_8","alias_value":"WE6ONQ4V","created_at":"2026-06-02T01:03:48.438154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.18141","citing_title":"A Brief Overview: On-Policy Self-Distillation In Large Language Models","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18141","citing_title":"A Brief Overview: On-Policy Self-Distillation In Large Language Models","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF","json":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF.json","graph_json":"https://pith.science/api/pith-number/WE6ONQ4VWP4JBDXVC7YOYNV5SF/graph.json","events_json":"https://pith.science/api/pith-number/WE6ONQ4VWP4JBDXVC7YOYNV5SF/events.json","paper":"https://pith.science/paper/WE6ONQ4V"},"agent_actions":{"view_html":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF","download_json":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF.json","view_paper":"https://pith.science/paper/WE6ONQ4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12400&json=true","fetch_graph":"https://pith.science/api/pith-number/WE6ONQ4VWP4JBDXVC7YOYNV5SF/graph.json","fetch_events":"https://pith.science/api/pith-number/WE6ONQ4VWP4JBDXVC7YOYNV5SF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF/action/storage_attestation","attest_author":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF/action/author_attestation","sign_citation":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF/action/citation_signature","submit_replication":"https://pith.science/pith/WE6ONQ4VWP4JBDXVC7YOYNV5SF/action/replication_record"}},"created_at":"2026-06-02T01:03:48.438154+00:00","updated_at":"2026-06-02T01:03:48.438154+00:00"}