{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AUVETHBOROWCZNMPXYYU6WNXLQ","short_pith_number":"pith:AUVETHBO","schema_version":"1.0","canonical_sha256":"052a499c2e8bac2cb58fbe314f59b75c2b78b26a4cc3bd403ea313e3d228ca04","source":{"kind":"arxiv","id":"2602.02405","version":2},"attestation_state":"computed","paper":{"title":"Making Expert Reasoning Learnable with Self-Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alan Ritter, Ethan Mendes, Jungsoo Park","submitted_at":"2026-02-02T18:03:43Z","abstract_excerpt":"Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or the existence of a stronger model able to solve the problem. However, many difficult problems remain intractable for even current frontier models, preventing the extraction of valid training signals. A promising alternative is to leverage high-quality expert human solutions, yet naive imitation of this data fails because it is fundamentally out-of-distribution: expert solutions are typically didactic, containing implicit reasoning "},"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":false},"canonical_record":{"source":{"id":"2602.02405","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T18:03:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af4b57059d7527e06cb3074880d5bb2d98f2d5d43654a4de6a91392227cd9056","abstract_canon_sha256":"69cb39da969183f5cad1154d44399379737f712f213990162b2c8b2c4e6c5756"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:41.191774Z","signature_b64":"C7JRUuNrwAZx5xq4brTDvewiFMckJqE0DG+vAY07HW0sczKBkgSZUJkChKqg5QxB/oZr644WqwuafoKFHA4WAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"052a499c2e8bac2cb58fbe314f59b75c2b78b26a4cc3bd403ea313e3d228ca04","last_reissued_at":"2026-06-04T01:08:41.191185Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:41.191185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Expert Reasoning Learnable with Self-Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alan Ritter, Ethan Mendes, Jungsoo Park","submitted_at":"2026-02-02T18:03:43Z","abstract_excerpt":"Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or the existence of a stronger model able to solve the problem. However, many difficult problems remain intractable for even current frontier models, preventing the extraction of valid training signals. A promising alternative is to leverage high-quality expert human solutions, yet naive imitation of this data fails because it is fundamentally out-of-distribution: expert solutions are typically didactic, containing implicit reasoning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02405","kind":"arxiv","version":2},"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/2602.02405/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.02405","created_at":"2026-06-04T01:08:41.191293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02405v2","created_at":"2026-06-04T01:08:41.191293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02405","created_at":"2026-06-04T01:08:41.191293+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUVETHBOROWC","created_at":"2026-06-04T01:08:41.191293+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUVETHBOROWCZNMP","created_at":"2026-06-04T01:08:41.191293+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUVETHBO","created_at":"2026-06-04T01:08:41.191293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13643","citing_title":"Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ","json":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ.json","graph_json":"https://pith.science/api/pith-number/AUVETHBOROWCZNMPXYYU6WNXLQ/graph.json","events_json":"https://pith.science/api/pith-number/AUVETHBOROWCZNMPXYYU6WNXLQ/events.json","paper":"https://pith.science/paper/AUVETHBO"},"agent_actions":{"view_html":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ","download_json":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ.json","view_paper":"https://pith.science/paper/AUVETHBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02405&json=true","fetch_graph":"https://pith.science/api/pith-number/AUVETHBOROWCZNMPXYYU6WNXLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AUVETHBOROWCZNMPXYYU6WNXLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ/action/storage_attestation","attest_author":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ/action/author_attestation","sign_citation":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ/action/citation_signature","submit_replication":"https://pith.science/pith/AUVETHBOROWCZNMPXYYU6WNXLQ/action/replication_record"}},"created_at":"2026-06-04T01:08:41.191293+00:00","updated_at":"2026-06-04T01:08:41.191293+00:00"}