{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q5FI6A25T3UQ5HM5UDEVOYH5W2","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":"fd65251b43d2383a77db151a092ffcc5d7a911efa3c17abe7be8da6edad4038d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T17:02:18Z","title_canon_sha256":"d2cf3df97570302a7ac17f1ad11113b5de7f58fbc980b2339f171bac6991711a"},"schema_version":"1.0","source":{"id":"2606.29502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29502","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29502v1","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29502","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"Q5FI6A25T3UQ","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"Q5FI6A25T3UQ5HM5","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"Q5FI6A25","created_at":"2026-06-30T01:18:09Z"}],"graph_snapshots":[{"event_id":"sha256:500ef88b256a8926fcf572dcbe75cf581b11d6811b1818c9c8903a27093597de","target":"graph","created_at":"2026-06-30T01:18:09Z","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/2606.29502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while misleading the same policy in another. This makes the common privileged-teacher assumption fragile, namely that a skill-conditioned prompt can be treated as a fixed teacher for the no-skill prompt. We introduce UCOB, a framework for learning to utilize and evolve agentic skills via credit-aware on-policy bidirectional self-distillation. UCOB treats skill-conditioned and no-skill prompts as two on-policy context views o","authors_text":"Chengdong Xu, Dongbin Zhao, Dong Li, Linjing Li, Qichao Zhang, Songjun Tu, Xiangyuan Lan, Yaocheng Zhang, Yiwen Ma","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T17:02:18Z","title":"UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29502","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":"sha256:4c15d1779ef7d12e069001173264ac03a835b7428b20817adff605f91944426c","target":"record","created_at":"2026-06-30T01:18:09Z","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":"fd65251b43d2383a77db151a092ffcc5d7a911efa3c17abe7be8da6edad4038d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T17:02:18Z","title_canon_sha256":"d2cf3df97570302a7ac17f1ad11113b5de7f58fbc980b2339f171bac6991711a"},"schema_version":"1.0","source":{"id":"2606.29502","kind":"arxiv","version":1}},"canonical_sha256":"874a8f035d9ee90e9d9da0c95760fdb6998015c761c02c3c9314c3b598f86f3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"874a8f035d9ee90e9d9da0c95760fdb6998015c761c02c3c9314c3b598f86f3c","first_computed_at":"2026-06-30T01:18:09.445667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:09.445667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NNUmIRvejF2gqd18vbu403UGt1rwf68CI6Q5eqQ+N1ySTVYgsPSJd3TS2jmb5WTpuRIkpuauuMUW8MmMblT5Ag==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:09.446248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c15d1779ef7d12e069001173264ac03a835b7428b20817adff605f91944426c","sha256:500ef88b256a8926fcf572dcbe75cf581b11d6811b1818c9c8903a27093597de"],"state_sha256":"f9860277a706d1280c11891147c9126f12fb8c2a3d3aca62da5e215ca417a23e"}