{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A2CYL6H224JPUN7KRFYGFIVII3","short_pith_number":"pith:A2CYL6H2","schema_version":"1.0","canonical_sha256":"068585f8fad712fa37ea897062a2a846f50aaf39c883955a24d57bf2a59d6814","source":{"kind":"arxiv","id":"2608.09228","version":1},"attestation_state":"computed","paper":{"title":"Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Junpei Komiyama, Mohammad Atif Quamar, Naoto Iwase, Yuki Ichihara","submitted_at":"2026-08-10T07:51:45Z","abstract_excerpt":"On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises the student's trajectory. However, this interpretation conflates two effects. The reference solution not only reveals the answer to the current instance but also changes the context under which the teacher provides token-level supervision. We investigate the role of target-specific privilege with $\\mathrm{OP}^{2}\\mathrm{SD}$ (On-Policy Self-Distillation from Other Problems), which replaces the paired reference with a"},"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":"2608.09228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T07:51:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dde7a4a3d4438b5d021668763bba0252c4de6f78b6905577932a49f6ee5ad77d","abstract_canon_sha256":"fa920c762d5ceda16e46314f905d5adcd9360c7e1488518f1afd0d4f668338bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:22:07.816143Z","signature_b64":"4fgkCjebWjQc3v4MZ5BXJ7wXzsmUD05ysOYwV1/Y349qnymQHNb+z6lMrx/U/0iQaVckWFtFKYyGiCeRz+yqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"068585f8fad712fa37ea897062a2a846f50aaf39c883955a24d57bf2a59d6814","last_reissued_at":"2026-08-11T02:22:07.814465Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:22:07.814465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Junpei Komiyama, Mohammad Atif Quamar, Naoto Iwase, Yuki Ichihara","submitted_at":"2026-08-10T07:51:45Z","abstract_excerpt":"On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises the student's trajectory. However, this interpretation conflates two effects. The reference solution not only reveals the answer to the current instance but also changes the context under which the teacher provides token-level supervision. We investigate the role of target-specific privilege with $\\mathrm{OP}^{2}\\mathrm{SD}$ (On-Policy Self-Distillation from Other Problems), which replaces the paired reference with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09228","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/2608.09228/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":"2608.09228","created_at":"2026-08-11T02:22:07.815156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09228v1","created_at":"2026-08-11T02:22:07.815156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09228","created_at":"2026-08-11T02:22:07.815156+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2CYL6H224JP","created_at":"2026-08-11T02:22:07.815156+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2CYL6H224JPUN7K","created_at":"2026-08-11T02:22:07.815156+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2CYL6H2","created_at":"2026-08-11T02:22:07.815156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3","json":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3.json","graph_json":"https://pith.science/api/pith-number/A2CYL6H224JPUN7KRFYGFIVII3/graph.json","events_json":"https://pith.science/api/pith-number/A2CYL6H224JPUN7KRFYGFIVII3/events.json","paper":"https://pith.science/paper/A2CYL6H2"},"agent_actions":{"view_html":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3","download_json":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3.json","view_paper":"https://pith.science/paper/A2CYL6H2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09228&json=true","fetch_graph":"https://pith.science/api/pith-number/A2CYL6H224JPUN7KRFYGFIVII3/graph.json","fetch_events":"https://pith.science/api/pith-number/A2CYL6H224JPUN7KRFYGFIVII3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3/action/storage_attestation","attest_author":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3/action/author_attestation","sign_citation":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3/action/citation_signature","submit_replication":"https://pith.science/pith/A2CYL6H224JPUN7KRFYGFIVII3/action/replication_record"}},"created_at":"2026-08-11T02:22:07.815156+00:00","updated_at":"2026-08-11T02:22:07.815156+00:00"}