{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VYRRYU5V2OEKDYPWCQYRMNVAL3","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":"7fe97636fab17b4355f8387a78ffe7816a48427627266cce0d06efe33a1316c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T13:20:39Z","title_canon_sha256":"7517ea9569d5c8ba3e685a6e043df15829e3b434f436d9b23ce412d245edcbb5"},"schema_version":"1.0","source":{"id":"2606.03620","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03620","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03620v1","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03620","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"VYRRYU5V2OEK","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"VYRRYU5V2OEKDYPW","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"VYRRYU5V","created_at":"2026-06-03T01:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:2c89725a421907666b981efb2d1a2fe30b4ce59e141127d1f109f1ce3c700569","target":"graph","created_at":"2026-06-03T01:06:02Z","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/2606.03620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-distilled policy optimization (SDPO) has become a popular paradigm for LLM post-training, where a model learns from its own predictions conditioned on privileged information. SDPO, however, is sensitive to how much each update step should be trusted: corrections from a self-teacher can be highly informative on some batches and misleading on others, and applying them uniformly with a fixed step size can destabilize training. Drawing inspiration from viscous-fluid dynamics and formalizing the analogy at the SDE level, we propose Physics-Guided Policy Optimization (PGPO), which introduces an","authors_text":"Chaoqun Jia, Devin Chen, Haoran Liu, Kai Wei, Ke Wang, Yuning Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T13:20:39Z","title":"Physics-Guided Policy Optimization with Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03620","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":"sha256:2cf5fd4bb6754d6674a12334fe050ec66b34e5bb47e22b7433f3523ddf57fe47","target":"record","created_at":"2026-06-03T01:06:02Z","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":"7fe97636fab17b4355f8387a78ffe7816a48427627266cce0d06efe33a1316c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T13:20:39Z","title_canon_sha256":"7517ea9569d5c8ba3e685a6e043df15829e3b434f436d9b23ce412d245edcbb5"},"schema_version":"1.0","source":{"id":"2606.03620","kind":"arxiv","version":1}},"canonical_sha256":"ae231c53b5d388a1e1f614311636a05ee61d2ad704ddaa61003708e5dbacef0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae231c53b5d388a1e1f614311636a05ee61d2ad704ddaa61003708e5dbacef0e","first_computed_at":"2026-06-03T01:06:02.527290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:06:02.527290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2TdNFuDuBiK9AYjL4ztB8BkBeOzaUed2C1pXaLmjBncTHFDG8taavCGzTHo6h2eRDeV05gXjUkur3dv7y4oWDg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:06:02.527647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03620","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cf5fd4bb6754d6674a12334fe050ec66b34e5bb47e22b7433f3523ddf57fe47","sha256:2c89725a421907666b981efb2d1a2fe30b4ce59e141127d1f109f1ce3c700569"],"state_sha256":"17ceb6f42147dca862ccc8e263d94fe3fd13c732ca703ab55ebbf6eeb3779cee"}