{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WZDIEVXIJMHH3MGHX7AMK2P3I5","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":"0fd90ecbd2e54d5a626a41e955b817fcb2184f0888f2cbfac8b100ec6085de19","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T13:21:30Z","title_canon_sha256":"644d206607f98eb73e2634218fa11c78bf4543c9ca63b8b4dd90b94b9777894b"},"schema_version":"1.0","source":{"id":"2606.00172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00172","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00172v1","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00172","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"WZDIEVXIJMHH","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"WZDIEVXIJMHH3MGH","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"WZDIEVXI","created_at":"2026-06-02T01:03:20Z"}],"graph_snapshots":[{"event_id":"sha256:bd5d03d13a621d9658dda242bc510579448bffcb099477f7c887819861da57a1","target":"graph","created_at":"2026-06-02T01:03:20Z","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/2606.00172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR), especially Group Relative Policy Optimization (GRPO), has been widely used to improve reasoning in large language models. However, outcome-level rewards provide only sparse supervision, and group-relative advantages vanish when all sampled trajectories for a prompt are either correct or incorrect. On-Policy Self-Distillation (OPSD) offers dense token-level guidance, but its token preferences are not necessarily aligned with trajectory correctness; empirical diagnostics show that OPSD signals behave differently on correct and incorrect roll","authors_text":"Gongle Xue, Lei Ma, Liwen Hu, Yang Li, Yijia Guo, Yuheng Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T13:21:30Z","title":"CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00172","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:a0a5029dd61a84a50189914532b38039e068818d13263e72784923f5f8f53c93","target":"record","created_at":"2026-06-02T01:03:20Z","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":"0fd90ecbd2e54d5a626a41e955b817fcb2184f0888f2cbfac8b100ec6085de19","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T13:21:30Z","title_canon_sha256":"644d206607f98eb73e2634218fa11c78bf4543c9ca63b8b4dd90b94b9777894b"},"schema_version":"1.0","source":{"id":"2606.00172","kind":"arxiv","version":1}},"canonical_sha256":"b6468256e84b0e7db0c7bfc0c569fb475a8050cd164dfdc623425f1d9618cdcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6468256e84b0e7db0c7bfc0c569fb475a8050cd164dfdc623425f1d9618cdcb","first_computed_at":"2026-06-02T01:03:20.502910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:20.502910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lYbHW9jBx2yGX4Y0yluuWKOUFgb0I5Ebpy6F6Cso3lY+W5RUVXbAVz2hfedMbArtoipIuvgHcgt5HReyL+ZTBg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:20.503245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0a5029dd61a84a50189914532b38039e068818d13263e72784923f5f8f53c93","sha256:bd5d03d13a621d9658dda242bc510579448bffcb099477f7c887819861da57a1"],"state_sha256":"d32e5e476b7daffd0c55ab3d9b80a19f9ee62daf3dac22dc4c109952cd2bf97f"}