{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2BLPPV5ZTN3Y3S7AMDX3MIDVXN","short_pith_number":"pith:2BLPPV5Z","canonical_record":{"source":{"id":"2607.14171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T09:37:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5e2f1bfd381708fcd099ed38c6d0fb69183c17fbf44563125eb408bfdbd7002f","abstract_canon_sha256":"35b2a9f9de71a1263aff23d9ecd2a0873c1be01b9670df887409275e36e84025"},"schema_version":"1.0"},"canonical_sha256":"d056f7d7b99b778dcbe060efb62075bb570a8da2fdd663dbf96ba17e16a6c06a","source":{"kind":"arxiv","id":"2607.14171","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14171","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14171v1","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14171","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"2BLPPV5ZTN3Y","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"2BLPPV5ZTN3Y3S7A","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"2BLPPV5Z","created_at":"2026-07-17T00:20:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2BLPPV5ZTN3Y3S7AMDX3MIDVXN","target":"record","payload":{"canonical_record":{"source":{"id":"2607.14171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T09:37:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5e2f1bfd381708fcd099ed38c6d0fb69183c17fbf44563125eb408bfdbd7002f","abstract_canon_sha256":"35b2a9f9de71a1263aff23d9ecd2a0873c1be01b9670df887409275e36e84025"},"schema_version":"1.0"},"canonical_sha256":"d056f7d7b99b778dcbe060efb62075bb570a8da2fdd663dbf96ba17e16a6c06a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:20:55.083410Z","signature_b64":"zA1TwQxarSDJA6oGPKF7t1On0IH1Nyw0yrSFPTGw7Dgo/Ws+iLKN/Y2QNysbCjb2tHh5OmYb989Cni4JZg53Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d056f7d7b99b778dcbe060efb62075bb570a8da2fdd663dbf96ba17e16a6c06a","last_reissued_at":"2026-07-17T00:20:55.082581Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:20:55.082581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.14171","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":"2026-07-17T00:20:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+wFhR5DhSZw7EgUtYLbun758GRNBPg1XdVFtt+WJJy1pd7c52zE4MLLkXOziK7ie5RNFLL9GJA6x3mBVx/g8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:42:51.213501Z"},"content_sha256":"4185914e143aad5197d299239c5ba4145f6d61d18d449b8da23b34986c773ece","schema_version":"1.0","event_id":"sha256:4185914e143aad5197d299239c5ba4145f6d61d18d449b8da23b34986c773ece"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2BLPPV5ZTN3Y3S7AMDX3MIDVXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bowei He, Xiaokun Zhang, Xue Liu, Yankai Chen","submitted_at":"2026-07-15T09:37:36Z","abstract_excerpt":"Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such as PPO, RLOO, and GRPO inherit their rollout topology from RLHF: for each prompt, N independent trajectories are sampled from the initial state, and an advantage is computed by subtracting a group baseline. This design ignores a defining property of agent sandboxes. They are deterministic, snapshottable, and resumable from any intermediate state. We argue that this property enables a fundamentally different rollout "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14171","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/2607.14171/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":"2026-07-17T00:20:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ttUJea5HLyAUKftziZx2aKtWw1di1tbAZwRvMyN0Emlt0GgfuruGh9Y4IAptPDOeuDrdSJnfrI1/GfzVPYhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:42:51.214037Z"},"content_sha256":"654d762c91d8975fad5a4c665669ede402c579105e4e8ecf12b637aef2179d4f","schema_version":"1.0","event_id":"sha256:654d762c91d8975fad5a4c665669ede402c579105e4e8ecf12b637aef2179d4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BLPPV5ZTN3Y3S7AMDX3MIDVXN/bundle.json","state_url":"https://pith.science/pith/2BLPPV5ZTN3Y3S7AMDX3MIDVXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BLPPV5ZTN3Y3S7AMDX3MIDVXN/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":"2026-08-06T04:42:51Z","links":{"resolver":"https://pith.science/pith/2BLPPV5ZTN3Y3S7AMDX3MIDVXN","bundle":"https://pith.science/pith/2BLPPV5ZTN3Y3S7AMDX3MIDVXN/bundle.json","state":"https://pith.science/pith/2BLPPV5ZTN3Y3S7AMDX3MIDVXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BLPPV5ZTN3Y3S7AMDX3MIDVXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2BLPPV5ZTN3Y3S7AMDX3MIDVXN","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":"35b2a9f9de71a1263aff23d9ecd2a0873c1be01b9670df887409275e36e84025","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T09:37:36Z","title_canon_sha256":"5e2f1bfd381708fcd099ed38c6d0fb69183c17fbf44563125eb408bfdbd7002f"},"schema_version":"1.0","source":{"id":"2607.14171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14171","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14171v1","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14171","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"2BLPPV5ZTN3Y","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"2BLPPV5ZTN3Y3S7A","created_at":"2026-07-17T00:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"2BLPPV5Z","created_at":"2026-07-17T00:20:55Z"}],"graph_snapshots":[{"event_id":"sha256:654d762c91d8975fad5a4c665669ede402c579105e4e8ecf12b637aef2179d4f","target":"graph","created_at":"2026-07-17T00:20:55Z","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/2607.14171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such as PPO, RLOO, and GRPO inherit their rollout topology from RLHF: for each prompt, N independent trajectories are sampled from the initial state, and an advantage is computed by subtracting a group baseline. This design ignores a defining property of agent sandboxes. They are deterministic, snapshottable, and resumable from any intermediate state. We argue that this property enables a fundamentally different rollout ","authors_text":"Bowei He, Xiaokun Zhang, Xue Liu, Yankai Chen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T09:37:36Z","title":"Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14171","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":"sha256:4185914e143aad5197d299239c5ba4145f6d61d18d449b8da23b34986c773ece","target":"record","created_at":"2026-07-17T00:20:55Z","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":"35b2a9f9de71a1263aff23d9ecd2a0873c1be01b9670df887409275e36e84025","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T09:37:36Z","title_canon_sha256":"5e2f1bfd381708fcd099ed38c6d0fb69183c17fbf44563125eb408bfdbd7002f"},"schema_version":"1.0","source":{"id":"2607.14171","kind":"arxiv","version":1}},"canonical_sha256":"d056f7d7b99b778dcbe060efb62075bb570a8da2fdd663dbf96ba17e16a6c06a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d056f7d7b99b778dcbe060efb62075bb570a8da2fdd663dbf96ba17e16a6c06a","first_computed_at":"2026-07-17T00:20:55.082581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:20:55.082581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zA1TwQxarSDJA6oGPKF7t1On0IH1Nyw0yrSFPTGw7Dgo/Ws+iLKN/Y2QNysbCjb2tHh5OmYb989Cni4JZg53Cg==","signature_status":"signed_v1","signed_at":"2026-07-17T00:20:55.083410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4185914e143aad5197d299239c5ba4145f6d61d18d449b8da23b34986c773ece","sha256:654d762c91d8975fad5a4c665669ede402c579105e4e8ecf12b637aef2179d4f"],"state_sha256":"a236c043ad8163f88eb76daad094ae77c7d000ce5a204baccdf6617965911dd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14T75P+YPGlZaGhiWIi1qwiuG2SRHd5t1smhkOccGpBeu1IUWfse+/6WbzQ/3KeFFXKfzbNevpIP6fs6oD1vDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:42:51.217491Z","bundle_sha256":"fa6cee27344d54718e1dcbb4321ae6ef6b025104fb47068fa859f35625bbfd5b"}}