{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JP753OZLGR675YT2PRMR6JY54G","short_pith_number":"pith:JP753OZL","canonical_record":{"source":{"id":"2607.02502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T17:58:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b4c258120733246ce79ba5350c370adc79a99e6c00c1c698a5293d2d3ae6dec","abstract_canon_sha256":"30442e905f26a6eddab174d4a00c4e655c242c39083b8554aa366091f9861649"},"schema_version":"1.0"},"canonical_sha256":"4bffddbb2b347dfee27a7c591f271de1adb0bd7ff80d45fb0510f0457adf008b","source":{"kind":"arxiv","id":"2607.02502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02502","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02502v1","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02502","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"JP753OZLGR67","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"JP753OZLGR675YT2","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"JP753OZL","created_at":"2026-07-03T01:18:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JP753OZLGR675YT2PRMR6JY54G","target":"record","payload":{"canonical_record":{"source":{"id":"2607.02502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T17:58:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b4c258120733246ce79ba5350c370adc79a99e6c00c1c698a5293d2d3ae6dec","abstract_canon_sha256":"30442e905f26a6eddab174d4a00c4e655c242c39083b8554aa366091f9861649"},"schema_version":"1.0"},"canonical_sha256":"4bffddbb2b347dfee27a7c591f271de1adb0bd7ff80d45fb0510f0457adf008b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:18:01.248521Z","signature_b64":"BtSAFm2Ai+WxkmkBALXYjT/d4+ISRL+3tmYGmE7YMTOddI97ijUlcYvegkChTMxavBtmFvbtScpSwY8ilRXRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bffddbb2b347dfee27a7c591f271de1adb0bd7ff80d45fb0510f0457adf008b","last_reissued_at":"2026-07-03T01:18:01.248130Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:18:01.248130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.02502","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":"2026-07-03T01:18:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NbgHs/eu/2yDI+/oJN7o9tYiv3EA+A2HQT86y+RjRzWHvyR1zGp/5zoMlUqOMhMtrBVAS4SyK0S2w4RglHdXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T23:38:49.404393Z"},"content_sha256":"59429dc4bab0afda99c75fa454a0b00d7ed1e1b4128580c9ef5cb2acdb94d925","schema_version":"1.0","event_id":"sha256:59429dc4bab0afda99c75fa454a0b00d7ed1e1b4128580c9ef5cb2acdb94d925"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JP753OZLGR675YT2PRMR6JY54G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DemoPSD: Disagreement-Modulated Policy Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hanxu Hou, Hao Shi, Linqi Song, Mengzhe Ruan, Shuang Qiu, Wenhao Liu, Yunhe Li, Zhongxiang Dai","submitted_at":"2026-07-02T17:58:29Z","abstract_excerpt":"On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain generalization, while also introducing a more fundamental issue: *privileged information leakage*, where the student encodes answer-dependent shortcuts that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02502","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/2607.02502/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":"2026-07-03T01:18:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kg6/9ljFTR1iVJ0/Mz+2F8KXBe0agVIlAQo/TFCcgppYP0Z6GViytzdvxaJoBOSXePQtomvySQw639qkYiBhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T23:38:49.404783Z"},"content_sha256":"dd919e304e671ef167bd4249aa10cfb92de8062e19b88ae5d193d7bc8b880afe","schema_version":"1.0","event_id":"sha256:dd919e304e671ef167bd4249aa10cfb92de8062e19b88ae5d193d7bc8b880afe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JP753OZLGR675YT2PRMR6JY54G/bundle.json","state_url":"https://pith.science/pith/JP753OZLGR675YT2PRMR6JY54G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JP753OZLGR675YT2PRMR6JY54G/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":"2026-07-03T23:38:49Z","links":{"resolver":"https://pith.science/pith/JP753OZLGR675YT2PRMR6JY54G","bundle":"https://pith.science/pith/JP753OZLGR675YT2PRMR6JY54G/bundle.json","state":"https://pith.science/pith/JP753OZLGR675YT2PRMR6JY54G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JP753OZLGR675YT2PRMR6JY54G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JP753OZLGR675YT2PRMR6JY54G","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":"30442e905f26a6eddab174d4a00c4e655c242c39083b8554aa366091f9861649","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T17:58:29Z","title_canon_sha256":"6b4c258120733246ce79ba5350c370adc79a99e6c00c1c698a5293d2d3ae6dec"},"schema_version":"1.0","source":{"id":"2607.02502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02502","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02502v1","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02502","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"JP753OZLGR67","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"JP753OZLGR675YT2","created_at":"2026-07-03T01:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"JP753OZL","created_at":"2026-07-03T01:18:01Z"}],"graph_snapshots":[{"event_id":"sha256:dd919e304e671ef167bd4249aa10cfb92de8062e19b88ae5d193d7bc8b880afe","target":"graph","created_at":"2026-07-03T01:18:01Z","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/2607.02502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain generalization, while also introducing a more fundamental issue: *privileged information leakage*, where the student encodes answer-dependent shortcuts that","authors_text":"Hanxu Hou, Hao Shi, Linqi Song, Mengzhe Ruan, Shuang Qiu, Wenhao Liu, Yunhe Li, Zhongxiang Dai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T17:58:29Z","title":"DemoPSD: Disagreement-Modulated Policy Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02502","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":"sha256:59429dc4bab0afda99c75fa454a0b00d7ed1e1b4128580c9ef5cb2acdb94d925","target":"record","created_at":"2026-07-03T01:18:01Z","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":"30442e905f26a6eddab174d4a00c4e655c242c39083b8554aa366091f9861649","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T17:58:29Z","title_canon_sha256":"6b4c258120733246ce79ba5350c370adc79a99e6c00c1c698a5293d2d3ae6dec"},"schema_version":"1.0","source":{"id":"2607.02502","kind":"arxiv","version":1}},"canonical_sha256":"4bffddbb2b347dfee27a7c591f271de1adb0bd7ff80d45fb0510f0457adf008b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bffddbb2b347dfee27a7c591f271de1adb0bd7ff80d45fb0510f0457adf008b","first_computed_at":"2026-07-03T01:18:01.248130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:18:01.248130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BtSAFm2Ai+WxkmkBALXYjT/d4+ISRL+3tmYGmE7YMTOddI97ijUlcYvegkChTMxavBtmFvbtScpSwY8ilRXRAQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:18:01.248521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59429dc4bab0afda99c75fa454a0b00d7ed1e1b4128580c9ef5cb2acdb94d925","sha256:dd919e304e671ef167bd4249aa10cfb92de8062e19b88ae5d193d7bc8b880afe"],"state_sha256":"1997fb329f5f1cb459ade34fc725029871b2db0c294c7cca14a8b6bb36161d0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G+6DcPHuzNMmMaEDuNBZPentUtefv1npyeIMDlCqCzL/Ue+Ja8R+GBUHKgz0OVg+lRL8DpyP5P8a1CBrlvx2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T23:38:49.407298Z","bundle_sha256":"597a0d3a8bb619cd2df41a9010453cfbf2e50d97b93a7885a915e17dc5b07bb3"}}