{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6ZPRPGCUYGMNXBHX5Q55MQYAPE","short_pith_number":"pith:6ZPRPGCU","canonical_record":{"source":{"id":"2608.19408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-19T19:45:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e639eeca80b2d5079f877b31a9df25ca43df12c3b4681fbc14ef29d760ca50d1","abstract_canon_sha256":"40f550a547e76f194b3c5600300e1bc7a4ae8a98c05f1d55734825636ab48f6d"},"schema_version":"1.0"},"canonical_sha256":"f65f179854c198db84f7ec3bd64300791fe76a2fd778e8e8dccff88854fc6670","source":{"kind":"arxiv","id":"2608.19408","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.19408","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2608.19408v1","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.19408","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"6ZPRPGCUYGMN","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"6ZPRPGCUYGMNXBHX","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"6ZPRPGCU","created_at":"2026-08-21T00:20:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6ZPRPGCUYGMNXBHX5Q55MQYAPE","target":"record","payload":{"canonical_record":{"source":{"id":"2608.19408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-19T19:45:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e639eeca80b2d5079f877b31a9df25ca43df12c3b4681fbc14ef29d760ca50d1","abstract_canon_sha256":"40f550a547e76f194b3c5600300e1bc7a4ae8a98c05f1d55734825636ab48f6d"},"schema_version":"1.0"},"canonical_sha256":"f65f179854c198db84f7ec3bd64300791fe76a2fd778e8e8dccff88854fc6670","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-21T00:20:43.838171Z","signature_b64":"Hi1UVaxLOqUIN7ciUiHYDcm/h58lpFmciLtPExb+NGFk27kqPMayBfyUb2mMwvHOcc5C5MSSxt1zoSUjbx3hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f65f179854c198db84f7ec3bd64300791fe76a2fd778e8e8dccff88854fc6670","last_reissued_at":"2026-08-21T00:20:43.835868Z","signature_status":"signed_v1","first_computed_at":"2026-08-21T00:20:43.835868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.19408","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":"2026-08-21T00:20:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qYLnVCtmvFzbDm1LHmioO5N3+6GUzkr7aM2qQaLlU99xwLsJ7vKkLGpCal4/X8l4NjwnRhnkd1U9z/WndFRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:52:38.120000Z"},"content_sha256":"432714c361455ca454b51c36c14f683e0881447f89785596d8ab74844f9f7dec","schema_version":"1.0","event_id":"sha256:432714c361455ca454b51c36c14f683e0881447f89785596d8ab74844f9f7dec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6ZPRPGCUYGMNXBHX5Q55MQYAPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chen Yang, Danny H.K. Tsang, Haiyuan Wan, Rengrong Xiong, Yize Chen","submitted_at":"2026-08-19T19:45:32Z","abstract_excerpt":"On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dense token-level supervision from a teacher. However, OPD implicitly assumes that teacher-derived rewards are an appropriate proxy for reasoning progress, and therefore treats all teacher feedback equally during policy optimization. While in practice, this assumption does not always hold. We observe that teacher-derived rewards often conflict with genuine reasoning progress, as reasoning steps with clear reasoning advancement may still receive low"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.19408","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/2608.19408/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":"2026-08-21T00:20:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x4s6anqmNEXm9jdlde8tk0Tl46rT9XDKMfylpLmyonNELfkhOstMFV/jMEDAywWfTlmHU0WAsh3D/r0t6gn4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:52:38.120693Z"},"content_sha256":"b9ca4d32bab77f2337c59ebf4b8464bf0559a5786a4df243e7a4f582d7b30da3","schema_version":"1.0","event_id":"sha256:b9ca4d32bab77f2337c59ebf4b8464bf0559a5786a4df243e7a4f582d7b30da3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ZPRPGCUYGMNXBHX5Q55MQYAPE/bundle.json","state_url":"https://pith.science/pith/6ZPRPGCUYGMNXBHX5Q55MQYAPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ZPRPGCUYGMNXBHX5Q55MQYAPE/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":"2026-08-22T17:52:38Z","links":{"resolver":"https://pith.science/pith/6ZPRPGCUYGMNXBHX5Q55MQYAPE","bundle":"https://pith.science/pith/6ZPRPGCUYGMNXBHX5Q55MQYAPE/bundle.json","state":"https://pith.science/pith/6ZPRPGCUYGMNXBHX5Q55MQYAPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ZPRPGCUYGMNXBHX5Q55MQYAPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6ZPRPGCUYGMNXBHX5Q55MQYAPE","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":"40f550a547e76f194b3c5600300e1bc7a4ae8a98c05f1d55734825636ab48f6d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-19T19:45:32Z","title_canon_sha256":"e639eeca80b2d5079f877b31a9df25ca43df12c3b4681fbc14ef29d760ca50d1"},"schema_version":"1.0","source":{"id":"2608.19408","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.19408","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2608.19408v1","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.19408","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"6ZPRPGCUYGMN","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"6ZPRPGCUYGMNXBHX","created_at":"2026-08-21T00:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"6ZPRPGCU","created_at":"2026-08-21T00:20:43Z"}],"graph_snapshots":[{"event_id":"sha256:b9ca4d32bab77f2337c59ebf4b8464bf0559a5786a4df243e7a4f582d7b30da3","target":"graph","created_at":"2026-08-21T00:20:43Z","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/2608.19408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dense token-level supervision from a teacher. However, OPD implicitly assumes that teacher-derived rewards are an appropriate proxy for reasoning progress, and therefore treats all teacher feedback equally during policy optimization. While in practice, this assumption does not always hold. We observe that teacher-derived rewards often conflict with genuine reasoning progress, as reasoning steps with clear reasoning advancement may still receive low","authors_text":"Chen Yang, Danny H.K. Tsang, Haiyuan Wan, Rengrong Xiong, Yize Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-19T19:45:32Z","title":"Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.19408","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":"sha256:432714c361455ca454b51c36c14f683e0881447f89785596d8ab74844f9f7dec","target":"record","created_at":"2026-08-21T00:20:43Z","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":"40f550a547e76f194b3c5600300e1bc7a4ae8a98c05f1d55734825636ab48f6d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-19T19:45:32Z","title_canon_sha256":"e639eeca80b2d5079f877b31a9df25ca43df12c3b4681fbc14ef29d760ca50d1"},"schema_version":"1.0","source":{"id":"2608.19408","kind":"arxiv","version":1}},"canonical_sha256":"f65f179854c198db84f7ec3bd64300791fe76a2fd778e8e8dccff88854fc6670","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f65f179854c198db84f7ec3bd64300791fe76a2fd778e8e8dccff88854fc6670","first_computed_at":"2026-08-21T00:20:43.835868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-21T00:20:43.835868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hi1UVaxLOqUIN7ciUiHYDcm/h58lpFmciLtPExb+NGFk27kqPMayBfyUb2mMwvHOcc5C5MSSxt1zoSUjbx3hBg==","signature_status":"signed_v1","signed_at":"2026-08-21T00:20:43.838171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.19408","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:432714c361455ca454b51c36c14f683e0881447f89785596d8ab74844f9f7dec","sha256:b9ca4d32bab77f2337c59ebf4b8464bf0559a5786a4df243e7a4f582d7b30da3"],"state_sha256":"85ae3fd4856a006f08274cb9bd400fefcc0155e3a66589e0daccf597664eb138"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EZrMobbVOnK1ggdwh9uMyPv1YXB3a9H5lupIzSVpykIS6ZhfOTGwLBwbT40nnD0ThbhNOkJprEH/jEwp7QoECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T17:52:38.125640Z","bundle_sha256":"1c7a4d585c40bbfb34c48c0652ab63d5d4322dd381b003460eb12258f444bfb4"}}