{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4ANSBTOAMV7JYW6L3VCM3UOFW5","short_pith_number":"pith:4ANSBTOA","canonical_record":{"source":{"id":"2606.09138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:35:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7237abc2927ccbdf3c1c9d78ca672602a009ded4a049c5030d0eca65bd93ced7","abstract_canon_sha256":"ccabaab71eb092e2e066422afea7661c429d2ea3404b8c6eb94d0f7d201809e9"},"schema_version":"1.0"},"canonical_sha256":"e01b20cdc0657e9c5bcbdd44cdd1c5b74afad87f6448e1c084043315416aed76","source":{"kind":"arxiv","id":"2606.09138","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09138","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09138v1","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09138","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"4ANSBTOAMV7J","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"4ANSBTOAMV7JYW6L","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"4ANSBTOA","created_at":"2026-06-09T02:08:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4ANSBTOAMV7JYW6L3VCM3UOFW5","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:35:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7237abc2927ccbdf3c1c9d78ca672602a009ded4a049c5030d0eca65bd93ced7","abstract_canon_sha256":"ccabaab71eb092e2e066422afea7661c429d2ea3404b8c6eb94d0f7d201809e9"},"schema_version":"1.0"},"canonical_sha256":"e01b20cdc0657e9c5bcbdd44cdd1c5b74afad87f6448e1c084043315416aed76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:01.472903Z","signature_b64":"KVrLbYsju4gsdTKtSRTQZ7UulvpAz5ILcIgkdmz+XOL6zmgqtWnF8z/TMxiKdRkOxMLZkgxbtnEyxDn6RxupDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e01b20cdc0657e9c5bcbdd44cdd1c5b74afad87f6448e1c084043315416aed76","last_reissued_at":"2026-06-09T02:08:01.471717Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:01.471717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09138","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEnK8DRDNv/JM4wt6AlnOqb4UaWL0K2qxdpUTleIdAHA9YRHZjaIaQ7jE9YOwzeP0cUme9frzzG+7IlrA0VQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T21:56:11.188546Z"},"content_sha256":"105ac4e07cb28c526f08cc60ca3c8f07f1345b602790afbacc1626347eb12063","schema_version":"1.0","event_id":"sha256:105ac4e07cb28c526f08cc60ca3c8f07f1345b602790afbacc1626347eb12063"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4ANSBTOAMV7JYW6L3VCM3UOFW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Daoyu Wang, Jie Ouyang, Mingyue Cheng, Qi Liu, Qingchuan Li, Shuo Yu","submitted_at":"2026-06-08T07:35:18Z","abstract_excerpt":"Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw. Existing work mainly focuses on policy optimization algorithms and training frameworks, but pays less attention to the full data lifecycle of agent-environment interactions, from data production to training consumption. To bridge this gap, we present Claw-R1, an interactive step-level data middleware system for agentic RL. Claw-R1 connects heterogeneous agent runtimes with RL training backe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09138","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.09138/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ykp8P9N+90IE5rDMJm7PhvyXVl8i+MD4f0RX25ADra7vO6d/ant/cihAtmhIwOZPz8jAHPV5TvHfvxCYLhGuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T21:56:11.189335Z"},"content_sha256":"fb85cec9caa7d5b7ae3155d4c878bdea4bb18f55145b0a428f535010881aa9dd","schema_version":"1.0","event_id":"sha256:fb85cec9caa7d5b7ae3155d4c878bdea4bb18f55145b0a428f535010881aa9dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ANSBTOAMV7JYW6L3VCM3UOFW5/bundle.json","state_url":"https://pith.science/pith/4ANSBTOAMV7JYW6L3VCM3UOFW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ANSBTOAMV7JYW6L3VCM3UOFW5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T21:56:11Z","links":{"resolver":"https://pith.science/pith/4ANSBTOAMV7JYW6L3VCM3UOFW5","bundle":"https://pith.science/pith/4ANSBTOAMV7JYW6L3VCM3UOFW5/bundle.json","state":"https://pith.science/pith/4ANSBTOAMV7JYW6L3VCM3UOFW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ANSBTOAMV7JYW6L3VCM3UOFW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4ANSBTOAMV7JYW6L3VCM3UOFW5","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":"ccabaab71eb092e2e066422afea7661c429d2ea3404b8c6eb94d0f7d201809e9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:35:18Z","title_canon_sha256":"7237abc2927ccbdf3c1c9d78ca672602a009ded4a049c5030d0eca65bd93ced7"},"schema_version":"1.0","source":{"id":"2606.09138","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09138","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09138v1","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09138","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"4ANSBTOAMV7J","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"4ANSBTOAMV7JYW6L","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"4ANSBTOA","created_at":"2026-06-09T02:08:01Z"}],"graph_snapshots":[{"event_id":"sha256:fb85cec9caa7d5b7ae3155d4c878bdea4bb18f55145b0a428f535010881aa9dd","target":"graph","created_at":"2026-06-09T02:08:01Z","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/2606.09138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw. Existing work mainly focuses on policy optimization algorithms and training frameworks, but pays less attention to the full data lifecycle of agent-environment interactions, from data production to training consumption. To bridge this gap, we present Claw-R1, an interactive step-level data middleware system for agentic RL. Claw-R1 connects heterogeneous agent runtimes with RL training backe","authors_text":"Daoyu Wang, Jie Ouyang, Mingyue Cheng, Qi Liu, Qingchuan Li, Shuo Yu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:35:18Z","title":"Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09138","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":"sha256:105ac4e07cb28c526f08cc60ca3c8f07f1345b602790afbacc1626347eb12063","target":"record","created_at":"2026-06-09T02:08:01Z","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":"ccabaab71eb092e2e066422afea7661c429d2ea3404b8c6eb94d0f7d201809e9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:35:18Z","title_canon_sha256":"7237abc2927ccbdf3c1c9d78ca672602a009ded4a049c5030d0eca65bd93ced7"},"schema_version":"1.0","source":{"id":"2606.09138","kind":"arxiv","version":1}},"canonical_sha256":"e01b20cdc0657e9c5bcbdd44cdd1c5b74afad87f6448e1c084043315416aed76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e01b20cdc0657e9c5bcbdd44cdd1c5b74afad87f6448e1c084043315416aed76","first_computed_at":"2026-06-09T02:08:01.471717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:01.471717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KVrLbYsju4gsdTKtSRTQZ7UulvpAz5ILcIgkdmz+XOL6zmgqtWnF8z/TMxiKdRkOxMLZkgxbtnEyxDn6RxupDw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:01.472903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09138","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:105ac4e07cb28c526f08cc60ca3c8f07f1345b602790afbacc1626347eb12063","sha256:fb85cec9caa7d5b7ae3155d4c878bdea4bb18f55145b0a428f535010881aa9dd"],"state_sha256":"1a31ccb787230b1703d4904216332eed4dce1d9cc4bf8b6a88f2ce1375fce1cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"snl2Zektx+ZE3WKTvpaK0KbLF8lp0a6N2af1MB6cc7psgWQzm9UTtXEUDWqmCPiZqradAotPmA9Aj8gFKGTOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T21:56:11.193821Z","bundle_sha256":"b8e0f700e8d04a4140abeaa7331d616e305134214a5f6e77c41227257a4ebce8"}}