{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LCTZHSOZBARZMLCZRGOMNOTWGT","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":"f75a7f0e782c4cca0714a147cb6142e9faba3aa1967d39bf0d7a15f64a89233d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T11:49:46Z","title_canon_sha256":"f4100bad5c864c513c1157acae13676e3aee044f93da353deb29a769d0315ef9"},"schema_version":"1.0","source":{"id":"2607.28076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28076","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28076v1","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28076","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"LCTZHSOZBARZ","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"LCTZHSOZBARZMLCZ","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"LCTZHSOZ","created_at":"2026-07-31T01:35:34Z"}],"graph_snapshots":[{"event_id":"sha256:fa7b1db4d51a0eb6f20ababce285429188a3e54dc4236250a24b01d391701c91","target":"graph","created_at":"2026-07-31T01:35:34Z","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/2607.28076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervision, leaving successful behaviors, recurring mistakes, and incidental choices entangled in the same outcome signal. Existing agentic self-distillation methods enrich sparse supervision with natural-language skills, but skills retrieved externally or extracted from a single trajectory by stronger models may mismatch current experience, exceed the policy's capability, or remain path-specific. We propose Group-Reflectiv","authors_text":"Binbin Zheng, Enlei Gong, Guanqun Zhao, Xiaoliang Fu, Xing Ma, Zeyu Chen, Zijun Xie","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T11:49:46Z","title":"Group-Reflective Self-Distillation for Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28076","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":"sha256:36df56b5704cfd8f540e978555dec3ba57ec3c31cdf496a661454c5fcb6dff20","target":"record","created_at":"2026-07-31T01:35:34Z","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":"f75a7f0e782c4cca0714a147cb6142e9faba3aa1967d39bf0d7a15f64a89233d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T11:49:46Z","title_canon_sha256":"f4100bad5c864c513c1157acae13676e3aee044f93da353deb29a769d0315ef9"},"schema_version":"1.0","source":{"id":"2607.28076","kind":"arxiv","version":1}},"canonical_sha256":"58a793c9d90823962c59899cc6ba7634eab931e97765a1a80a90550741a05387","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58a793c9d90823962c59899cc6ba7634eab931e97765a1a80a90550741a05387","first_computed_at":"2026-07-31T01:35:34.038999Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:35:34.038999Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36df56b5704cfd8f540e978555dec3ba57ec3c31cdf496a661454c5fcb6dff20","sha256:fa7b1db4d51a0eb6f20ababce285429188a3e54dc4236250a24b01d391701c91"],"state_sha256":"c552d06e6a11233d1af4c0ddf038af863ba5931cfca4dc118ad8b23cd2d19ee5"}