{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LP4KFZY3CV7GO4XQ66AT7UOQXR","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":"bd2cd98671c91c74f67c1b157034fbe6ced10a20ee7f0fa64129a7285f3722d8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T16:52:31Z","title_canon_sha256":"e9e988780aa74ca57097cd4763ca4c0e416ad0fb71fc246eb23c59202b51aa73"},"schema_version":"1.0","source":{"id":"2606.03892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03892","created_at":"2026-06-03T02:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03892v1","created_at":"2026-06-03T02:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03892","created_at":"2026-06-03T02:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"LP4KFZY3CV7G","created_at":"2026-06-03T02:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"LP4KFZY3CV7GO4XQ","created_at":"2026-06-03T02:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"LP4KFZY3","created_at":"2026-06-03T02:06:06Z"}],"graph_snapshots":[{"event_id":"sha256:3c0cbcd314b74ce6609f063939757edfd878c39d216b4131a503283181c43dff","target":"graph","created_at":"2026-06-03T02:06:06Z","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/2606.03892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns. We present PROVE (Programmatic Rewards On Verified Environments), a framework with three contributions: (1) a library of 20 stateful MCP (Model Context Protocol) servers exposing 343 tools, enabling live-execution RL training with session-scoped stat","authors_text":"Asim Munawar, Chulaka Gunasekara, Ibrahim Abdelaziz, Kinjal Basu, Maxwell Crouse, Pavan Kapanipathi, Suneet Katrekar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T16:52:31Z","title":"Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03892","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:dd054905fa9a43f785f39572f80774f13d379f94998d5a9f179b817d0ac62aba","target":"record","created_at":"2026-06-03T02:06:06Z","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":"bd2cd98671c91c74f67c1b157034fbe6ced10a20ee7f0fa64129a7285f3722d8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T16:52:31Z","title_canon_sha256":"e9e988780aa74ca57097cd4763ca4c0e416ad0fb71fc246eb23c59202b51aa73"},"schema_version":"1.0","source":{"id":"2606.03892","kind":"arxiv","version":1}},"canonical_sha256":"5bf8a2e71b157e6772f0f7813fd1d0bc420fd06493993702134d7918ca5ee80b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bf8a2e71b157e6772f0f7813fd1d0bc420fd06493993702134d7918ca5ee80b","first_computed_at":"2026-06-03T02:06:06.175776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:06.175776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tTh1Z0JCTUoYJ2Ki8vB4k4rQgU25e+ZBMT6ZaSEbJnHE79NVq3+nebsJ+vT6xNThGkLT8e10vnsigDh6ADJrDQ==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:06.176180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd054905fa9a43f785f39572f80774f13d379f94998d5a9f179b817d0ac62aba","sha256:3c0cbcd314b74ce6609f063939757edfd878c39d216b4131a503283181c43dff"],"state_sha256":"03194b194097c4f2a2d995ea941363a270793bb200da359cfbb99bc9f14e2675"}