{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SKEVQJJGRI7WNWAV7EEYH6IK2Y","short_pith_number":"pith:SKEVQJJG","canonical_record":{"source":{"id":"2608.07935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-08T05:46:32Z","cross_cats_sorted":[],"title_canon_sha256":"c0a42dec3aa3d34154d3ce3b644a4f76599f63e4e1d1a1d017ce49089510146e","abstract_canon_sha256":"a742ba9e07913d460d682710800b9786d5ad344aa325c6612d5cfdf29bc70094"},"schema_version":"1.0"},"canonical_sha256":"92895825268a3f66d815f90983f90ad63a6c4dce352032655b833595adc32bcf","source":{"kind":"arxiv","id":"2608.07935","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07935","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07935v1","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07935","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"SKEVQJJGRI7W","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"SKEVQJJGRI7WNWAV","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"SKEVQJJG","created_at":"2026-08-11T01:19:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SKEVQJJGRI7WNWAV7EEYH6IK2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2608.07935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-08T05:46:32Z","cross_cats_sorted":[],"title_canon_sha256":"c0a42dec3aa3d34154d3ce3b644a4f76599f63e4e1d1a1d017ce49089510146e","abstract_canon_sha256":"a742ba9e07913d460d682710800b9786d5ad344aa325c6612d5cfdf29bc70094"},"schema_version":"1.0"},"canonical_sha256":"92895825268a3f66d815f90983f90ad63a6c4dce352032655b833595adc32bcf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:19:03.007369Z","signature_b64":"nXdc5goLr5JOR5j7GWbct7mIbWc1hr6yT90l8GojlU9+TfMQrnIOZBctrpFA1Nf2Q/lMKruzqJtJwki0R7W4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92895825268a3f66d815f90983f90ad63a6c4dce352032655b833595adc32bcf","last_reissued_at":"2026-08-11T01:19:03.002711Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:19:03.002711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.07935","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":"2026-08-11T01:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVMBcRPZSyTQpvP0IDkiULaudzh+Kn/bBzKsh46LfTn8hhGyv2/iYPbtueSrZuaixMVdHLlOo0grYHiLoGRKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:15:39.449488Z"},"content_sha256":"9ff64c2d7fe7902cb8a30c50719dd91fa3e09f169e6509afffa8e49c0485200c","schema_version":"1.0","event_id":"sha256:9ff64c2d7fe7902cb8a30c50719dd91fa3e09f169e6509afffa8e49c0485200c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SKEVQJJGRI7WNWAV7EEYH6IK2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Supervised Anchoring for On-Policy Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Beijing, China), Jianhao Nie, Li Yu (1), Meilin Yang, Weite Zhang, Yuxin Zhang, Zhe Fu (1) ((1) Renmin University of China, Zhiming Shao, Zixuan Ding (1)","submitted_at":"2026-08-08T05:46:32Z","abstract_excerpt":"On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student. Its effectiveness, however, depends critically on the quality of those trajectories. We show that when student rollouts drift from target trajectories, conditioning the teacher on off-target prefixes substantially weakens its task-relevant supervision. Controlled prefix-corruption experiments expose this failure mode, which we term rollout-conditioned signal degradation. To address this problem, we propose a unified training framework that separates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07935","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/2608.07935/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":"2026-08-11T01:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d6zXfB4WCRP4z+DEsI1hfiBcTt0f5syByeTDHG14m7PgJMp7VexewJI3kwRRHFHhot97lHmd2lgbbyxhV26vAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:15:39.449824Z"},"content_sha256":"f3bda15d8b3df79f3ef39785a349ec4671122a4db5dc150619f8efb7ed7a6fd4","schema_version":"1.0","event_id":"sha256:f3bda15d8b3df79f3ef39785a349ec4671122a4db5dc150619f8efb7ed7a6fd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKEVQJJGRI7WNWAV7EEYH6IK2Y/bundle.json","state_url":"https://pith.science/pith/SKEVQJJGRI7WNWAV7EEYH6IK2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKEVQJJGRI7WNWAV7EEYH6IK2Y/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":"2026-08-20T17:15:39Z","links":{"resolver":"https://pith.science/pith/SKEVQJJGRI7WNWAV7EEYH6IK2Y","bundle":"https://pith.science/pith/SKEVQJJGRI7WNWAV7EEYH6IK2Y/bundle.json","state":"https://pith.science/pith/SKEVQJJGRI7WNWAV7EEYH6IK2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKEVQJJGRI7WNWAV7EEYH6IK2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SKEVQJJGRI7WNWAV7EEYH6IK2Y","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":"a742ba9e07913d460d682710800b9786d5ad344aa325c6612d5cfdf29bc70094","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-08T05:46:32Z","title_canon_sha256":"c0a42dec3aa3d34154d3ce3b644a4f76599f63e4e1d1a1d017ce49089510146e"},"schema_version":"1.0","source":{"id":"2608.07935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07935","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07935v1","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07935","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"SKEVQJJGRI7W","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"SKEVQJJGRI7WNWAV","created_at":"2026-08-11T01:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"SKEVQJJG","created_at":"2026-08-11T01:19:03Z"}],"graph_snapshots":[{"event_id":"sha256:f3bda15d8b3df79f3ef39785a349ec4671122a4db5dc150619f8efb7ed7a6fd4","target":"graph","created_at":"2026-08-11T01:19:03Z","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/2608.07935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student. Its effectiveness, however, depends critically on the quality of those trajectories. We show that when student rollouts drift from target trajectories, conditioning the teacher on off-target prefixes substantially weakens its task-relevant supervision. Controlled prefix-corruption experiments expose this failure mode, which we term rollout-conditioned signal degradation. To address this problem, we propose a unified training framework that separates ","authors_text":"Beijing, China), Jianhao Nie, Li Yu (1), Meilin Yang, Weite Zhang, Yuxin Zhang, Zhe Fu (1) ((1) Renmin University of China, Zhiming Shao, Zixuan Ding (1)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-08T05:46:32Z","title":"Adaptive Supervised Anchoring for On-Policy Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07935","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":"sha256:9ff64c2d7fe7902cb8a30c50719dd91fa3e09f169e6509afffa8e49c0485200c","target":"record","created_at":"2026-08-11T01:19:03Z","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":"a742ba9e07913d460d682710800b9786d5ad344aa325c6612d5cfdf29bc70094","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-08T05:46:32Z","title_canon_sha256":"c0a42dec3aa3d34154d3ce3b644a4f76599f63e4e1d1a1d017ce49089510146e"},"schema_version":"1.0","source":{"id":"2608.07935","kind":"arxiv","version":1}},"canonical_sha256":"92895825268a3f66d815f90983f90ad63a6c4dce352032655b833595adc32bcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92895825268a3f66d815f90983f90ad63a6c4dce352032655b833595adc32bcf","first_computed_at":"2026-08-11T01:19:03.002711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:19:03.002711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nXdc5goLr5JOR5j7GWbct7mIbWc1hr6yT90l8GojlU9+TfMQrnIOZBctrpFA1Nf2Q/lMKruzqJtJwki0R7W4CQ==","signature_status":"signed_v1","signed_at":"2026-08-11T01:19:03.007369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ff64c2d7fe7902cb8a30c50719dd91fa3e09f169e6509afffa8e49c0485200c","sha256:f3bda15d8b3df79f3ef39785a349ec4671122a4db5dc150619f8efb7ed7a6fd4"],"state_sha256":"95fa4665fd09c4d2d8c925224378dc37bc9584e5a23c41f323369adbfb604a96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUZYarhsSjo0lH7j7W/LT4ZWw3cB01NT0kNuyz8adZ1TazoPbitqyI+OTLC1TtRSmOnJuLdpVSxkFn76Ey03BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:15:39.452865Z","bundle_sha256":"f9b9fc1519a75a4be19b700c94bb6c50a25dde07ac0a71999193ded35bbe29ef"}}