{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MZPCQMLFE2S6KICUVDQ4JCEFLC","short_pith_number":"pith:MZPCQMLF","canonical_record":{"source":{"id":"2607.05458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T22:11:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54321d93674921a54662265b1e6818472702832b8f7013dfb4ece3d141221099","abstract_canon_sha256":"82aab22d72e9dd5df73e46a78be8168c35a1af08450b1bc7682edf5bdabf97a7"},"schema_version":"1.0"},"canonical_sha256":"665e28316526a5e52054a8e1c4888558aa0070360123dfcd1f17088301f4376d","source":{"kind":"arxiv","id":"2607.05458","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05458","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05458v1","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05458","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"MZPCQMLFE2S6","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"MZPCQMLFE2S6KICU","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"MZPCQMLF","created_at":"2026-07-08T01:18:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MZPCQMLFE2S6KICUVDQ4JCEFLC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T22:11:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54321d93674921a54662265b1e6818472702832b8f7013dfb4ece3d141221099","abstract_canon_sha256":"82aab22d72e9dd5df73e46a78be8168c35a1af08450b1bc7682edf5bdabf97a7"},"schema_version":"1.0"},"canonical_sha256":"665e28316526a5e52054a8e1c4888558aa0070360123dfcd1f17088301f4376d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:10.545606Z","signature_b64":"/NSP7n3r23hqQKGptAQnNO2w4udC5J9UVOK/WO404GOB4D493DSCUkUiLI1+1X7wmMp+7XyY63TrSyh70ED6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"665e28316526a5e52054a8e1c4888558aa0070360123dfcd1f17088301f4376d","last_reissued_at":"2026-07-08T01:18:10.545174Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:10.545174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05458","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":"2026-07-08T01:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b7aEQr2F5KQMt9JU1eGcfWcbzf9194A6SBbxHmzONel2zs8JKFqrLTo5nMU6HLGGrsxl96HFSDpNkObaST5eBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:30:36.864482Z"},"content_sha256":"277a5acc103cc4f6e377c2ac48936c8a3be6b11af6e32e1296f9f251c93ae374","schema_version":"1.0","event_id":"sha256:277a5acc103cc4f6e377c2ac48936c8a3be6b11af6e32e1296f9f251c93ae374"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MZPCQMLFE2S6KICUVDQ4JCEFLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haiwen Yi, Xinyuan Song","submitted_at":"2026-07-05T22:11:18Z","abstract_excerpt":"Large language model (LLM) agents are usually improved by changing prompts, models, or hand-written workflows, while the execution harness around the model is treated as fixed infrastructure. We argue that this harness is itself a learnable control layer. We formalize harness operation as a finite-horizon Harness MDP, where a lightweight controller selects structural execution actions while the LLM executor remains frozen. The controller is trained from offline rollouts using advantage-weighted regression with only terminal task-rubric rewards. We also separate final task quality from a post-h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05458","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/2607.05458/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":"2026-07-08T01:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"stXtS+/Ot/zqMHCH5o2+eFBxoKl0nUm4Lpo+qD668h6hmRHKdAEUyyYoY+t7rRXO5Ew0vTvNdH80ANxso3E+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:30:36.865343Z"},"content_sha256":"300d1d4bd449660d4b4ff56f7a72dc5d5f0323836e0a77c9e2140aaf213c69a1","schema_version":"1.0","event_id":"sha256:300d1d4bd449660d4b4ff56f7a72dc5d5f0323836e0a77c9e2140aaf213c69a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZPCQMLFE2S6KICUVDQ4JCEFLC/bundle.json","state_url":"https://pith.science/pith/MZPCQMLFE2S6KICUVDQ4JCEFLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZPCQMLFE2S6KICUVDQ4JCEFLC/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":"2026-08-03T15:30:36Z","links":{"resolver":"https://pith.science/pith/MZPCQMLFE2S6KICUVDQ4JCEFLC","bundle":"https://pith.science/pith/MZPCQMLFE2S6KICUVDQ4JCEFLC/bundle.json","state":"https://pith.science/pith/MZPCQMLFE2S6KICUVDQ4JCEFLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZPCQMLFE2S6KICUVDQ4JCEFLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MZPCQMLFE2S6KICUVDQ4JCEFLC","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":"82aab22d72e9dd5df73e46a78be8168c35a1af08450b1bc7682edf5bdabf97a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T22:11:18Z","title_canon_sha256":"54321d93674921a54662265b1e6818472702832b8f7013dfb4ece3d141221099"},"schema_version":"1.0","source":{"id":"2607.05458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05458","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05458v1","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05458","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"MZPCQMLFE2S6","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"MZPCQMLFE2S6KICU","created_at":"2026-07-08T01:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"MZPCQMLF","created_at":"2026-07-08T01:18:10Z"}],"graph_snapshots":[{"event_id":"sha256:300d1d4bd449660d4b4ff56f7a72dc5d5f0323836e0a77c9e2140aaf213c69a1","target":"graph","created_at":"2026-07-08T01:18:10Z","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/2607.05458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents are usually improved by changing prompts, models, or hand-written workflows, while the execution harness around the model is treated as fixed infrastructure. We argue that this harness is itself a learnable control layer. We formalize harness operation as a finite-horizon Harness MDP, where a lightweight controller selects structural execution actions while the LLM executor remains frozen. The controller is trained from offline rollouts using advantage-weighted regression with only terminal task-rubric rewards. We also separate final task quality from a post-h","authors_text":"Haiwen Yi, Xinyuan Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T22:11:18Z","title":"Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05458","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":"sha256:277a5acc103cc4f6e377c2ac48936c8a3be6b11af6e32e1296f9f251c93ae374","target":"record","created_at":"2026-07-08T01:18:10Z","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":"82aab22d72e9dd5df73e46a78be8168c35a1af08450b1bc7682edf5bdabf97a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T22:11:18Z","title_canon_sha256":"54321d93674921a54662265b1e6818472702832b8f7013dfb4ece3d141221099"},"schema_version":"1.0","source":{"id":"2607.05458","kind":"arxiv","version":1}},"canonical_sha256":"665e28316526a5e52054a8e1c4888558aa0070360123dfcd1f17088301f4376d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"665e28316526a5e52054a8e1c4888558aa0070360123dfcd1f17088301f4376d","first_computed_at":"2026-07-08T01:18:10.545174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:10.545174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/NSP7n3r23hqQKGptAQnNO2w4udC5J9UVOK/WO404GOB4D493DSCUkUiLI1+1X7wmMp+7XyY63TrSyh70ED6DQ==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:10.545606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:277a5acc103cc4f6e377c2ac48936c8a3be6b11af6e32e1296f9f251c93ae374","sha256:300d1d4bd449660d4b4ff56f7a72dc5d5f0323836e0a77c9e2140aaf213c69a1"],"state_sha256":"2e0b880815fe991ab96dd15d01cb1b5975a0989a18da603773239ad001de584d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q+injWqVlxx/V3BlM61K0FSmiqhhFK+n3UV3K+EFvEiG72Kou8Q/fuhLDw51b92UQUiBdl7vQLdsWL45uLbvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:30:36.871126Z","bundle_sha256":"459b47a8483480a2d0091020d83a45a908d9b46a0893270bcbddd759da8f81aa"}}