{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B7P5WTF6BFSRUKUGXX2YEA663Y","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":"79595b86dd79cfe87f744f1f1883fb85ccff7dabe6b22ed965c7ab4258791abd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T03:47:48Z","title_canon_sha256":"4ebf20e5e78d7fca9742d96871769fd3c3fef90331aec7f1559cfc877ed75fb8"},"schema_version":"1.0","source":{"id":"2606.03108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03108","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03108v1","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03108","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"B7P5WTF6BFSR","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"B7P5WTF6BFSRUKUG","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"B7P5WTF6","created_at":"2026-06-03T01:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:b443555948ff1f7b2241977eaecbea9a65a2f9a36672c4436bb0e2963c0b0e91","target":"graph","created_at":"2026-06-03T01:05:31Z","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/2606.03108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering","authors_text":"Binhua Li, Guhong Chen, Hu Wei, Jieping Ye, Min Yang, Shiwen Ni, Xander Xu, Yingcheng Shi, Yongbin Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T03:47:48Z","title":"EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03108","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":"sha256:2df2af3573828516daea9112f486dfc15a643a4fd29712db2080aa8d93e77fb5","target":"record","created_at":"2026-06-03T01:05:31Z","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":"79595b86dd79cfe87f744f1f1883fb85ccff7dabe6b22ed965c7ab4258791abd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T03:47:48Z","title_canon_sha256":"4ebf20e5e78d7fca9742d96871769fd3c3fef90331aec7f1559cfc877ed75fb8"},"schema_version":"1.0","source":{"id":"2606.03108","kind":"arxiv","version":1}},"canonical_sha256":"0fdfdb4cbe09651a2a86bdf58203dede123f36603e06f7c49be19416c15eb4e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fdfdb4cbe09651a2a86bdf58203dede123f36603e06f7c49be19416c15eb4e9","first_computed_at":"2026-06-03T01:05:31.935524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:31.935524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WJAhbnRNsVVJtkNxZ45kbWf/joUyXLlhrGSC+K9c0gNnRtoKLu5vZvZvrdDnOJDFp1904Ca3h/A7Nr+Pm4eADg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:31.935943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2df2af3573828516daea9112f486dfc15a643a4fd29712db2080aa8d93e77fb5","sha256:b443555948ff1f7b2241977eaecbea9a65a2f9a36672c4436bb0e2963c0b0e91"],"state_sha256":"a80ed524b29a43f689a0d2b4e8dcc84670b5d40c70e27372044ef1731570fb6d"}