{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BNZXF5KULTWBQ6BSIJVD2JNTEY","short_pith_number":"pith:BNZXF5KU","canonical_record":{"source":{"id":"2506.23667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T09:44:32Z","cross_cats_sorted":[],"title_canon_sha256":"0daaf7b6e27aa3f67e9db2cb29cde38f2f7247845aa76a6a4b875820852b1ae6","abstract_canon_sha256":"3cedaecc795614e927186c3e20dc4388efddc7bf9598b2c6dabead6443173e0e"},"schema_version":"1.0"},"canonical_sha256":"0b7372f5545cec187832426a3d25b326046d92634a3fc4b070cd5c6c194c4f19","source":{"kind":"arxiv","id":"2506.23667","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23667","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23667v1","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23667","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_12","alias_value":"BNZXF5KULTWB","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_16","alias_value":"BNZXF5KULTWBQ6BS","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_8","alias_value":"BNZXF5KU","created_at":"2026-07-05T11:29:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BNZXF5KULTWBQ6BSIJVD2JNTEY","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T09:44:32Z","cross_cats_sorted":[],"title_canon_sha256":"0daaf7b6e27aa3f67e9db2cb29cde38f2f7247845aa76a6a4b875820852b1ae6","abstract_canon_sha256":"3cedaecc795614e927186c3e20dc4388efddc7bf9598b2c6dabead6443173e0e"},"schema_version":"1.0"},"canonical_sha256":"0b7372f5545cec187832426a3d25b326046d92634a3fc4b070cd5c6c194c4f19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:26.059614Z","signature_b64":"MTgyj1yrk3lnpNbVW6QEq32CZ+/jlTUoglaReKQWj1xOnFTv+IfLLrL8yzRe9yukvkY9WDoZtQBjgb6A+OduAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b7372f5545cec187832426a3d25b326046d92634a3fc4b070cd5c6c194c4f19","last_reissued_at":"2026-07-05T11:29:26.059104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:26.059104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23667","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":"2026-07-05T11:29:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZH8IVEPh8ZUTJ3++IoPr9IY+45eeEEJJZzaRr3IQoaC5aObg3ut1OGzqPL54GP0K98tnExowaH5UIIo77mzDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:11:48.195380Z"},"content_sha256":"b893d488e9f4423bd65a66f12d686e59b70bdf933ea27b9d09f182f28513eba0","schema_version":"1.0","event_id":"sha256:b893d488e9f4423bd65a66f12d686e59b70bdf933ea27b9d09f182f28513eba0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BNZXF5KULTWBQ6BSIJVD2JNTEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"L0: Reinforcement Learning to Become General Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaxing Zhang, Jingyi Xi, Junjie Zhang, Junyu Lu, Songxin Zhang, Ting Sun, Yuhua Ke, Yukun Yang, Zejian Xie, Zhuoyang Song","submitted_at":"2025-06-30T09:44:32Z","abstract_excerpt":"Training large language models (LLMs) to act as autonomous agents for multi-turn, long-horizon tasks remains significant challenges in scalability and training efficiency. To address this, we introduce L-Zero (L0), a scalable, end-to-end training pipeline for general-purpose agents. Featuring a low-cost, extensible, and sandboxed concurrent agent worker pool, L0 lowers the barrier for applying reinforcement learning in complex environments. We also introduce NB-Agent, the agent scaffold within L0, which operates in a \"code-as-action\" fashion via a Read-Eval-Print-Loop (REPL). We evaluate L0 on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23667","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/2506.23667/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":"2026-07-05T11:29:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i85ng1B7+gkEZjneI/+NVuVcfEwOjvIz6bByY1cmHWvWsZ2prKAj5rRuI8x0rgpdFywuLsoFBFb8rdPZeBPZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:11:48.195882Z"},"content_sha256":"94a9cf152befe72cffcf39451caa77f62cfa581020bc653fcf41d6d65412db3c","schema_version":"1.0","event_id":"sha256:94a9cf152befe72cffcf39451caa77f62cfa581020bc653fcf41d6d65412db3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BNZXF5KULTWBQ6BSIJVD2JNTEY/bundle.json","state_url":"https://pith.science/pith/BNZXF5KULTWBQ6BSIJVD2JNTEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BNZXF5KULTWBQ6BSIJVD2JNTEY/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":"2026-08-09T06:11:48Z","links":{"resolver":"https://pith.science/pith/BNZXF5KULTWBQ6BSIJVD2JNTEY","bundle":"https://pith.science/pith/BNZXF5KULTWBQ6BSIJVD2JNTEY/bundle.json","state":"https://pith.science/pith/BNZXF5KULTWBQ6BSIJVD2JNTEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BNZXF5KULTWBQ6BSIJVD2JNTEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BNZXF5KULTWBQ6BSIJVD2JNTEY","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":"3cedaecc795614e927186c3e20dc4388efddc7bf9598b2c6dabead6443173e0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T09:44:32Z","title_canon_sha256":"0daaf7b6e27aa3f67e9db2cb29cde38f2f7247845aa76a6a4b875820852b1ae6"},"schema_version":"1.0","source":{"id":"2506.23667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23667","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23667v1","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23667","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_12","alias_value":"BNZXF5KULTWB","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_16","alias_value":"BNZXF5KULTWBQ6BS","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_8","alias_value":"BNZXF5KU","created_at":"2026-07-05T11:29:26Z"}],"graph_snapshots":[{"event_id":"sha256:94a9cf152befe72cffcf39451caa77f62cfa581020bc653fcf41d6d65412db3c","target":"graph","created_at":"2026-07-05T11:29:26Z","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/2506.23667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) to act as autonomous agents for multi-turn, long-horizon tasks remains significant challenges in scalability and training efficiency. To address this, we introduce L-Zero (L0), a scalable, end-to-end training pipeline for general-purpose agents. Featuring a low-cost, extensible, and sandboxed concurrent agent worker pool, L0 lowers the barrier for applying reinforcement learning in complex environments. We also introduce NB-Agent, the agent scaffold within L0, which operates in a \"code-as-action\" fashion via a Read-Eval-Print-Loop (REPL). We evaluate L0 on","authors_text":"Jiaxing Zhang, Jingyi Xi, Junjie Zhang, Junyu Lu, Songxin Zhang, Ting Sun, Yuhua Ke, Yukun Yang, Zejian Xie, Zhuoyang Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T09:44:32Z","title":"L0: Reinforcement Learning to Become General Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23667","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:b893d488e9f4423bd65a66f12d686e59b70bdf933ea27b9d09f182f28513eba0","target":"record","created_at":"2026-07-05T11:29:26Z","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":"3cedaecc795614e927186c3e20dc4388efddc7bf9598b2c6dabead6443173e0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T09:44:32Z","title_canon_sha256":"0daaf7b6e27aa3f67e9db2cb29cde38f2f7247845aa76a6a4b875820852b1ae6"},"schema_version":"1.0","source":{"id":"2506.23667","kind":"arxiv","version":1}},"canonical_sha256":"0b7372f5545cec187832426a3d25b326046d92634a3fc4b070cd5c6c194c4f19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b7372f5545cec187832426a3d25b326046d92634a3fc4b070cd5c6c194c4f19","first_computed_at":"2026-07-05T11:29:26.059104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:26.059104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MTgyj1yrk3lnpNbVW6QEq32CZ+/jlTUoglaReKQWj1xOnFTv+IfLLrL8yzRe9yukvkY9WDoZtQBjgb6A+OduAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:26.059614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b893d488e9f4423bd65a66f12d686e59b70bdf933ea27b9d09f182f28513eba0","sha256:94a9cf152befe72cffcf39451caa77f62cfa581020bc653fcf41d6d65412db3c"],"state_sha256":"4109149fe57d911f1e9db89da4ecd7687bc048dceab11e6e33567124e9e22c6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6zp/vLRYWpikd60TPeW/bn3nrxqtANzuaTwSwOqhxSSsBdEsKkx+iD7OsjVyYmEmhFfm8Z7cheVtbLr366IKAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:11:48.200533Z","bundle_sha256":"0a7c73f3c0cddb158232cebf6a2909843bc1ad426af230b478e4033a9708dc92"}}