{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LOB7LANO7WPL6FWZWNTZM6XWFQ","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":"ece4f74cefbc25e1d07ce25a093301d8322afa747386cd298827148169543d2c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T06:56:47Z","title_canon_sha256":"921cbd13b831a249b27d11aa443fdeaf2025a2b18a7a68b371c054242f5c5a0c"},"schema_version":"1.0","source":{"id":"2608.03223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03223","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03223v1","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03223","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"LOB7LANO7WPL","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"LOB7LANO7WPL6FWZ","created_at":"2026-08-05T00:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"LOB7LANO","created_at":"2026-08-05T00:46:19Z"}],"graph_snapshots":[{"event_id":"sha256:9c240e0c581140d075c16c489951ddab27e0aeef7bec044f744dc7513021a68a","target":"graph","created_at":"2026-08-05T00:46:19Z","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/2608.03223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit. Training-only privileged skills can provide denser supervision by allowing the same frozen policy snapshot to rescore fixed tokens from skill-free trajectories while conditioned on task-matched procedural skills. Existing methods, however, do not jointly calibrate teacher scores across interaction steps, relate teacher confidence to realized returns, and integrate the resulting signal into native rewa","authors_text":"Chao Wang, Chenshaodong, Guinan Chen, Jinghao Lin, Ranxu zhang, Sunzhe, Xiaozhou Xu, Yanyong Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T06:56:47Z","title":"Agentic Reinforcement Learning with Self-Distilled Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03223","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":"sha256:42ae4f054a00355172275b2f0d32b18cd609d744357aaf513387059e41ec8de3","target":"record","created_at":"2026-08-05T00:46:19Z","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":"ece4f74cefbc25e1d07ce25a093301d8322afa747386cd298827148169543d2c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T06:56:47Z","title_canon_sha256":"921cbd13b831a249b27d11aa443fdeaf2025a2b18a7a68b371c054242f5c5a0c"},"schema_version":"1.0","source":{"id":"2608.03223","kind":"arxiv","version":1}},"canonical_sha256":"5b83f581aefd9ebf16d9b367967af62c2005965cb951e02ab7ae08278533a55c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b83f581aefd9ebf16d9b367967af62c2005965cb951e02ab7ae08278533a55c","first_computed_at":"2026-08-05T00:46:19.193946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:46:19.193946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fKOG6urzcACLI8KW/pE+jBq6mX/JpDKnM57+iUA88NV8Qr4kKNlbcmsmIzQPQMWG8eZxPUgS4Ek9PsYgK6xHAg==","signature_status":"signed_v1","signed_at":"2026-08-05T00:46:19.196340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42ae4f054a00355172275b2f0d32b18cd609d744357aaf513387059e41ec8de3","sha256:9c240e0c581140d075c16c489951ddab27e0aeef7bec044f744dc7513021a68a"],"state_sha256":"8445496e706363e6facc3d12825d2bb3941657aa9c930341ae0d79e81c1797b4"}