{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4KFQZ4ID33B5YVETS4V5VJWJDG","short_pith_number":"pith:4KFQZ4ID","canonical_record":{"source":{"id":"2605.22263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"08d1640b9aede080c9360fa2374dbbdb58813fb03256bbdc8cc2b28e66a221e4","abstract_canon_sha256":"8e68bfd1cc43d7be412cb9346ec62a72ddecb4eef73040c182cdecbced0fab3a"},"schema_version":"1.0"},"canonical_sha256":"e28b0cf103dec3dc5493972bdaa6c919aa6aea9e9dd4bad93208d24f3a249fe7","source":{"kind":"arxiv","id":"2605.22263","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22263","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22263v1","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22263","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"4KFQZ4ID33B5","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"4KFQZ4ID33B5YVET","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"4KFQZ4ID","created_at":"2026-05-22T01:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4KFQZ4ID33B5YVETS4V5VJWJDG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"08d1640b9aede080c9360fa2374dbbdb58813fb03256bbdc8cc2b28e66a221e4","abstract_canon_sha256":"8e68bfd1cc43d7be412cb9346ec62a72ddecb4eef73040c182cdecbced0fab3a"},"schema_version":"1.0"},"canonical_sha256":"e28b0cf103dec3dc5493972bdaa6c919aa6aea9e9dd4bad93208d24f3a249fe7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:35.124996Z","signature_b64":"QzWzP5DwQPoF6XnW4afyLzMi+vCpS2HSViUNMWYYn8lFEN5lkJKjZADgqVXCP8phD+/ZSdYMiW7mSkrCJzV8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e28b0cf103dec3dc5493972bdaa6c919aa6aea9e9dd4bad93208d24f3a249fe7","last_reissued_at":"2026-05-22T01:04:35.124222Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:35.124222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22263","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":"2026-05-22T01:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IUR28j14BaPTpLpWqIyTlbW9keZsi0552gtqcg32CZYIQzWymGXKx7wu0XaifFZzs/dP0R4oTcKmug1tzf+/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T07:03:11.139906Z"},"content_sha256":"bd92be3acec018e1cd0acf00ae433012923a40a7ca4c6dbfcf614b8e756a5c85","schema_version":"1.0","event_id":"sha256:bd92be3acec018e1cd0acf00ae433012923a40a7ca4c6dbfcf614b8e756a5c85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4KFQZ4ID33B5YVETS4V5VJWJDG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaozheng Wang, Hongbin Zhang, Jinpeng Wang, Kehai Chen, Min Zhang, Yang Xiang, Youcheng Pan","submitted_at":"2026-05-21T10:07:46Z","abstract_excerpt":"On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides dense token-level supervision on its own rollouts. However, recent studies show that OPSD degrades complex reasoning by suppressing predictive uncertainty, which supports exploration and hypothesis revision. Our token-level analysis shows that this failure arises from applying a uniform direction of teacher supervision across tokens with different uncertainty levels: conformit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22263","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/2605.22263/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":"2026-05-22T01:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oIzkHq8RVHnDMMiRwBffduiYbj7qHt5MiXJvSfjuI2Yt3DU5d2F2P5eCQd47XbKlkZvH0O6V+yhjL5vFIE53Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T07:03:11.140298Z"},"content_sha256":"0e761465734d27df513d90abf95e2ef5631f1528de80f11255586c6d79e940b8","schema_version":"1.0","event_id":"sha256:0e761465734d27df513d90abf95e2ef5631f1528de80f11255586c6d79e940b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KFQZ4ID33B5YVETS4V5VJWJDG/bundle.json","state_url":"https://pith.science/pith/4KFQZ4ID33B5YVETS4V5VJWJDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KFQZ4ID33B5YVETS4V5VJWJDG/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":"2026-05-23T07:03:11Z","links":{"resolver":"https://pith.science/pith/4KFQZ4ID33B5YVETS4V5VJWJDG","bundle":"https://pith.science/pith/4KFQZ4ID33B5YVETS4V5VJWJDG/bundle.json","state":"https://pith.science/pith/4KFQZ4ID33B5YVETS4V5VJWJDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KFQZ4ID33B5YVETS4V5VJWJDG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4KFQZ4ID33B5YVETS4V5VJWJDG","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":"8e68bfd1cc43d7be412cb9346ec62a72ddecb4eef73040c182cdecbced0fab3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46Z","title_canon_sha256":"08d1640b9aede080c9360fa2374dbbdb58813fb03256bbdc8cc2b28e66a221e4"},"schema_version":"1.0","source":{"id":"2605.22263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22263","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22263v1","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22263","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"4KFQZ4ID33B5","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"4KFQZ4ID33B5YVET","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"4KFQZ4ID","created_at":"2026-05-22T01:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:0e761465734d27df513d90abf95e2ef5631f1528de80f11255586c6d79e940b8","target":"graph","created_at":"2026-05-22T01:04:35Z","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/2605.22263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides dense token-level supervision on its own rollouts. However, recent studies show that OPSD degrades complex reasoning by suppressing predictive uncertainty, which supports exploration and hypothesis revision. Our token-level analysis shows that this failure arises from applying a uniform direction of teacher supervision across tokens with different uncertainty levels: conformit","authors_text":"Chaozheng Wang, Hongbin Zhang, Jinpeng Wang, Kehai Chen, Min Zhang, Yang Xiang, Youcheng Pan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46Z","title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22263","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:bd92be3acec018e1cd0acf00ae433012923a40a7ca4c6dbfcf614b8e756a5c85","target":"record","created_at":"2026-05-22T01:04:35Z","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":"8e68bfd1cc43d7be412cb9346ec62a72ddecb4eef73040c182cdecbced0fab3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46Z","title_canon_sha256":"08d1640b9aede080c9360fa2374dbbdb58813fb03256bbdc8cc2b28e66a221e4"},"schema_version":"1.0","source":{"id":"2605.22263","kind":"arxiv","version":1}},"canonical_sha256":"e28b0cf103dec3dc5493972bdaa6c919aa6aea9e9dd4bad93208d24f3a249fe7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e28b0cf103dec3dc5493972bdaa6c919aa6aea9e9dd4bad93208d24f3a249fe7","first_computed_at":"2026-05-22T01:04:35.124222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:35.124222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QzWzP5DwQPoF6XnW4afyLzMi+vCpS2HSViUNMWYYn8lFEN5lkJKjZADgqVXCP8phD+/ZSdYMiW7mSkrCJzV8AA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:35.124996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd92be3acec018e1cd0acf00ae433012923a40a7ca4c6dbfcf614b8e756a5c85","sha256:0e761465734d27df513d90abf95e2ef5631f1528de80f11255586c6d79e940b8"],"state_sha256":"9805fe6c3d3e2ab90937695d27e40970677042a23d1a7de09ff3e8e719db53d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9hXdQfeBgKZWrJ/SU/17rpWnNBV2hm3sg2kT7jjim56BFHg/vdPw2jKVh6Mfar4ZW93I8WGwulfQmL6VL22pCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T07:03:11.144336Z","bundle_sha256":"5536037e28a0ad5b2d1056f2f36721cb2890817d1ec76e17475a22aee8071c4e"}}