{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SZ5BGYO7FRFCEOEV6NMR4BZNEG","short_pith_number":"pith:SZ5BGYO7","canonical_record":{"source":{"id":"2605.24220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-22T21:06:12Z","cross_cats_sorted":[],"title_canon_sha256":"5bd37c575e610e09fd1e1623f749624d0cd5f02e102e55e537d6eba1c44d6487","abstract_canon_sha256":"c2a343bdd8017fb93c88122cac8d8f1fc5a046b3223b50f52a5f6c06923e558c"},"schema_version":"1.0"},"canonical_sha256":"967a1361df2c4a223895f3591e072d21adb43f20901ef41047427853f988e98e","source":{"kind":"arxiv","id":"2605.24220","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24220","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24220v1","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24220","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_12","alias_value":"SZ5BGYO7FRFC","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_16","alias_value":"SZ5BGYO7FRFCEOEV","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_8","alias_value":"SZ5BGYO7","created_at":"2026-05-26T01:02:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SZ5BGYO7FRFCEOEV6NMR4BZNEG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-22T21:06:12Z","cross_cats_sorted":[],"title_canon_sha256":"5bd37c575e610e09fd1e1623f749624d0cd5f02e102e55e537d6eba1c44d6487","abstract_canon_sha256":"c2a343bdd8017fb93c88122cac8d8f1fc5a046b3223b50f52a5f6c06923e558c"},"schema_version":"1.0"},"canonical_sha256":"967a1361df2c4a223895f3591e072d21adb43f20901ef41047427853f988e98e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:53.216326Z","signature_b64":"Q1+6mR+pnDIm6+qis7DzFHIwKHbQtprn1KVtERAk0lkq5jKEqMG792cD6WbrHa1htSFT5qyj2yC2AKYjUDAHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"967a1361df2c4a223895f3591e072d21adb43f20901ef41047427853f988e98e","last_reissued_at":"2026-05-26T01:02:53.215535Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:53.215535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24220","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":"2026-05-26T01:02:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HQsoZd+Nf6RNnLeu1vsPhsABm1kLDrerGLUeCHOY9wXN0EUTFfoYM7foCf4vktCSZpI3qYXhohKXhnlagv+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:24:36.301479Z"},"content_sha256":"0c67d0dce580346e73830d07f6cf52e13971c89d24ab58f6a03b17f8b1562ffa","schema_version":"1.0","event_id":"sha256:0c67d0dce580346e73830d07f6cf52e13971c89d24ab58f6a03b17f8b1562ffa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SZ5BGYO7FRFCEOEV6NMR4BZNEG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Polar: Agentic RL on Any Harness at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Binfeng Xu, Hao Zhang, Jan Kautz, Jian Hu, Michael Demoret, Mingjie Liu, Shaokun Zhang, Shizhe Diao, Songyang Han, Yi Dong, Yunheng Zou, Zhenghui Jin","submitted_at":"2026-05-22T21:06:12Z","abstract_excerpt":"Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, porting these harnesses into RL environment interfaces remains difficult and often loses important training signals. We bridge this gap with polar, a rollout framework for scalable asynchronous RL over arbitrary agent harnesses. Polar treats the agent harness as a black box: it proxies LLM API calls, records token-level model interactions, and reconstructs token-faithful trajectories for training. Each rollout node eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24220","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/2605.24220/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":"2026-05-26T01:02:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FXrkCZlrmibLtGgwEnouTtAiJvr1Vl3k1oMpdbeVTnc7Bd6bGp1HNVMXFPAKmbOat/rJSCQ5fGHKUmtLLvJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:24:36.301847Z"},"content_sha256":"034d17a6878f133996b91772ade1d37f093081b2ea0729771c40e591356c85ca","schema_version":"1.0","event_id":"sha256:034d17a6878f133996b91772ade1d37f093081b2ea0729771c40e591356c85ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZ5BGYO7FRFCEOEV6NMR4BZNEG/bundle.json","state_url":"https://pith.science/pith/SZ5BGYO7FRFCEOEV6NMR4BZNEG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZ5BGYO7FRFCEOEV6NMR4BZNEG/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":"2026-06-02T23:24:36Z","links":{"resolver":"https://pith.science/pith/SZ5BGYO7FRFCEOEV6NMR4BZNEG","bundle":"https://pith.science/pith/SZ5BGYO7FRFCEOEV6NMR4BZNEG/bundle.json","state":"https://pith.science/pith/SZ5BGYO7FRFCEOEV6NMR4BZNEG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZ5BGYO7FRFCEOEV6NMR4BZNEG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SZ5BGYO7FRFCEOEV6NMR4BZNEG","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":"c2a343bdd8017fb93c88122cac8d8f1fc5a046b3223b50f52a5f6c06923e558c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-22T21:06:12Z","title_canon_sha256":"5bd37c575e610e09fd1e1623f749624d0cd5f02e102e55e537d6eba1c44d6487"},"schema_version":"1.0","source":{"id":"2605.24220","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24220","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24220v1","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24220","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_12","alias_value":"SZ5BGYO7FRFC","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_16","alias_value":"SZ5BGYO7FRFCEOEV","created_at":"2026-05-26T01:02:53Z"},{"alias_kind":"pith_short_8","alias_value":"SZ5BGYO7","created_at":"2026-05-26T01:02:53Z"}],"graph_snapshots":[{"event_id":"sha256:034d17a6878f133996b91772ade1d37f093081b2ea0729771c40e591356c85ca","target":"graph","created_at":"2026-05-26T01:02:53Z","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/2605.24220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, porting these harnesses into RL environment interfaces remains difficult and often loses important training signals. We bridge this gap with polar, a rollout framework for scalable asynchronous RL over arbitrary agent harnesses. Polar treats the agent harness as a black box: it proxies LLM API calls, records token-level model interactions, and reconstructs token-faithful trajectories for training. Each rollout node eff","authors_text":"Binfeng Xu, Hao Zhang, Jan Kautz, Jian Hu, Michael Demoret, Mingjie Liu, Shaokun Zhang, Shizhe Diao, Songyang Han, Yi Dong, Yunheng Zou, Zhenghui Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-22T21:06:12Z","title":"Polar: Agentic RL on Any Harness at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24220","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":"sha256:0c67d0dce580346e73830d07f6cf52e13971c89d24ab58f6a03b17f8b1562ffa","target":"record","created_at":"2026-05-26T01:02:53Z","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":"c2a343bdd8017fb93c88122cac8d8f1fc5a046b3223b50f52a5f6c06923e558c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-22T21:06:12Z","title_canon_sha256":"5bd37c575e610e09fd1e1623f749624d0cd5f02e102e55e537d6eba1c44d6487"},"schema_version":"1.0","source":{"id":"2605.24220","kind":"arxiv","version":1}},"canonical_sha256":"967a1361df2c4a223895f3591e072d21adb43f20901ef41047427853f988e98e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"967a1361df2c4a223895f3591e072d21adb43f20901ef41047427853f988e98e","first_computed_at":"2026-05-26T01:02:53.215535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:53.215535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q1+6mR+pnDIm6+qis7DzFHIwKHbQtprn1KVtERAk0lkq5jKEqMG792cD6WbrHa1htSFT5qyj2yC2AKYjUDAHDg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:53.216326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24220","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c67d0dce580346e73830d07f6cf52e13971c89d24ab58f6a03b17f8b1562ffa","sha256:034d17a6878f133996b91772ade1d37f093081b2ea0729771c40e591356c85ca"],"state_sha256":"fb9df99fe78cef859c241caf71f3e6411912870beab8dfdefa12f64694bb0821"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OTqQFD0zHhil1FF3z6aBxCCt9tIjB+yJw+0OsfZbjId4D1vdBVxQQIM6n4slHKoG2gJOIWq9YqcMhF+EW7m1CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:24:36.303835Z","bundle_sha256":"936ed337238981c317d4a75175973bf319de13cfca1c46054dfedd5ea4e1634e"}}