{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WZDIEVXIJMHH3MGHX7AMK2P3I5","short_pith_number":"pith:WZDIEVXI","schema_version":"1.0","canonical_sha256":"b6468256e84b0e7db0c7bfc0c569fb475a8050cd164dfdc623425f1d9618cdcb","source":{"kind":"arxiv","id":"2606.00172","version":1},"attestation_state":"computed","paper":{"title":"CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gongle Xue, Lei Ma, Liwen Hu, Yang Li, Yijia Guo, Yuheng Yuan","submitted_at":"2026-05-29T13:21:30Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.00172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T13:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"644d206607f98eb73e2634218fa11c78bf4543c9ca63b8b4dd90b94b9777894b","abstract_canon_sha256":"0fd90ecbd2e54d5a626a41e955b817fcb2184f0888f2cbfac8b100ec6085de19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:20.503245Z","signature_b64":"lYbHW9jBx2yGX4Y0yluuWKOUFgb0I5Ebpy6F6Cso3lY+W5RUVXbAVz2hfedMbArtoipIuvgHcgt5HReyL+ZTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6468256e84b0e7db0c7bfc0c569fb475a8050cd164dfdc623425f1d9618cdcb","last_reissued_at":"2026-06-02T01:03:20.502910Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:20.502910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gongle Xue, Lei Ma, Liwen Hu, Yang Li, Yijia Guo, Yuheng Yuan","submitted_at":"2026-05-29T13:21:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00172","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/2606.00172/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.00172","created_at":"2026-06-02T01:03:20.502965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00172v1","created_at":"2026-06-02T01:03:20.502965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00172","created_at":"2026-06-02T01:03:20.502965+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZDIEVXIJMHH","created_at":"2026-06-02T01:03:20.502965+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZDIEVXIJMHH3MGH","created_at":"2026-06-02T01:03:20.502965+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZDIEVXI","created_at":"2026-06-02T01:03:20.502965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5","json":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5.json","graph_json":"https://pith.science/api/pith-number/WZDIEVXIJMHH3MGHX7AMK2P3I5/graph.json","events_json":"https://pith.science/api/pith-number/WZDIEVXIJMHH3MGHX7AMK2P3I5/events.json","paper":"https://pith.science/paper/WZDIEVXI"},"agent_actions":{"view_html":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5","download_json":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5.json","view_paper":"https://pith.science/paper/WZDIEVXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00172&json=true","fetch_graph":"https://pith.science/api/pith-number/WZDIEVXIJMHH3MGHX7AMK2P3I5/graph.json","fetch_events":"https://pith.science/api/pith-number/WZDIEVXIJMHH3MGHX7AMK2P3I5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5/action/storage_attestation","attest_author":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5/action/author_attestation","sign_citation":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5/action/citation_signature","submit_replication":"https://pith.science/pith/WZDIEVXIJMHH3MGHX7AMK2P3I5/action/replication_record"}},"created_at":"2026-06-02T01:03:20.502965+00:00","updated_at":"2026-06-02T01:03:20.502965+00:00"}