{"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"}