{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F6Z2Z74BKSJGNNEL6XDCP627XX","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":"306891138c5c7e8944faa4bfe599da9abb799622561373e09ff13d6486ddc5bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T03:13:35Z","title_canon_sha256":"1ddef559a4b7e6b3304eaee3872651972b76a89d230a62fc6a34eb4059cae21d"},"schema_version":"1.0","source":{"id":"2605.15565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15565","created_at":"2026-05-20T00:01:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15565v1","created_at":"2026-05-20T00:01:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15565","created_at":"2026-05-20T00:01:05Z"},{"alias_kind":"pith_short_12","alias_value":"F6Z2Z74BKSJG","created_at":"2026-05-20T00:01:05Z"},{"alias_kind":"pith_short_16","alias_value":"F6Z2Z74BKSJGNNEL","created_at":"2026-05-20T00:01:05Z"},{"alias_kind":"pith_short_8","alias_value":"F6Z2Z74B","created_at":"2026-05-20T00:01:05Z"}],"graph_snapshots":[{"event_id":"sha256:0f88f48c054892eec6b593d8ef9d4b4d5ff27eb5c4c5b8d4087489f6b51108d7","target":"graph","created_at":"2026-05-20T00:01:05Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:35.258419Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.083500Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15565/integrity.json","findings":[],"snapshot_sha256":"10fdad04b0cfda9e5cc32def93cf8cad15bcb1fa416fb80da18af902b5f015d3","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensive. Scaling RL to agentic LLMs requires supporting complex workloads, including multi-policy collaborative training, while efficiently using elastic, heterogeneous, and cross-region compute resources. Existing LLM RL systems support some of these capabilities, but each new extension often requires dedicated system engineering. This burden arises from trainer-centered control architectures and the lack of principled ab","authors_text":"Beidi Chen, Haizhong Zheng, Ion Stoica, Jiahui Wang, Jiawei Zhao, Shuowei Jin, Xueshen Liu, Yizhuo Di, Yongji Wu, Z. Morley Mao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T03:13:35Z","title":"AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15565","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:fe2308d7728cf645fcf5c306cb04e464db75bfa2dfbca394b7e57d2f03d7b4de","target":"record","created_at":"2026-05-20T00:01:05Z","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":"306891138c5c7e8944faa4bfe599da9abb799622561373e09ff13d6486ddc5bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T03:13:35Z","title_canon_sha256":"1ddef559a4b7e6b3304eaee3872651972b76a89d230a62fc6a34eb4059cae21d"},"schema_version":"1.0","source":{"id":"2605.15565","kind":"arxiv","version":1}},"canonical_sha256":"2fb3acff81549266b48bf5c627fb5fbdcf39eaa887e6b061f5d7557a70c03d98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fb3acff81549266b48bf5c627fb5fbdcf39eaa887e6b061f5d7557a70c03d98","first_computed_at":"2026-05-20T00:01:05.667791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:05.667791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VM7GGzioUFCeeEg7lXkBd0W5VbSdEd4IrfoO/S+Mer7O37GSnNy8RuwJaxoc9NQfxS4ADC1zS+/lQ/n5mAflBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:05.668707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe2308d7728cf645fcf5c306cb04e464db75bfa2dfbca394b7e57d2f03d7b4de","sha256:0f88f48c054892eec6b593d8ef9d4b4d5ff27eb5c4c5b8d4087489f6b51108d7"],"state_sha256":"40902b075e93148ce3b15c5724ab712a528f660c2cfef843d8600a7beac255f1"}