{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DY6SHWTIE2HRRVK5RWVBUPCEKU","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":"d13795186ec9628d766c4b6e188a5ba3eca5bc73a3154ddc4dfdc1e1b2176d58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T21:00:50Z","title_canon_sha256":"7c0208ccdc562ef175b837dcf6114e7c797df32c674252da4d3312287aafd278"},"schema_version":"1.0","source":{"id":"2607.15457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15457","created_at":"2026-07-20T00:18:35Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15457v1","created_at":"2026-07-20T00:18:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15457","created_at":"2026-07-20T00:18:35Z"},{"alias_kind":"pith_short_12","alias_value":"DY6SHWTIE2HR","created_at":"2026-07-20T00:18:35Z"},{"alias_kind":"pith_short_16","alias_value":"DY6SHWTIE2HRRVK5","created_at":"2026-07-20T00:18:35Z"},{"alias_kind":"pith_short_8","alias_value":"DY6SHWTI","created_at":"2026-07-20T00:18:35Z"}],"graph_snapshots":[{"event_id":"sha256:83ceee55150ab2ecc57b1dec52d2a7bbf2f4ec3d4a51267029d854a14b0a0ee8","target":"graph","created_at":"2026-07-20T00:18:35Z","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/2607.15457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study robust peak-cost constrained reinforcement learning (RP-CRL), where the objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory. This setting is motivated by safety-critical applications in which a single large violation can be catastrophic and therefore cannot be adequately captured by the standard CMDP framework based on expected cumulative cost. Existing reachability-constrained RL methods adopt Lagrangian-based approaches, yet the underlying duality properties of peak-cost constrained MDPs remain unclear. We show that, unlike stan","authors_text":"Arnob Ghosh, Debdipta Goswami, Honghao Wei, Santosh Mohan Rajkumar, Shilpa Mukhopadhyay, Sourav Ganguly","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T21:00:50Z","title":"Robust Peak-cost Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15457","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":"sha256:45641bc9fd81c306c7768a6894d9012b408bea42d2fae42bcb0caf0906f3983f","target":"record","created_at":"2026-07-20T00:18:35Z","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":"d13795186ec9628d766c4b6e188a5ba3eca5bc73a3154ddc4dfdc1e1b2176d58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T21:00:50Z","title_canon_sha256":"7c0208ccdc562ef175b837dcf6114e7c797df32c674252da4d3312287aafd278"},"schema_version":"1.0","source":{"id":"2607.15457","kind":"arxiv","version":1}},"canonical_sha256":"1e3d23da68268f18d55d8daa1a3c4455000d988e06f2fee1f35a815bc8b1e2ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e3d23da68268f18d55d8daa1a3c4455000d988e06f2fee1f35a815bc8b1e2ce","first_computed_at":"2026-07-20T00:18:35.022083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T00:18:35.022083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p28aVYtkEmduJavQl6wbHLv/BZy4k/fkrXC1zuP7pL62KqDO/1lUJykiQrXbtvkxbZ6FYRWdWKUEqCRf0I9hDg==","signature_status":"signed_v1","signed_at":"2026-07-20T00:18:35.022931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45641bc9fd81c306c7768a6894d9012b408bea42d2fae42bcb0caf0906f3983f","sha256:83ceee55150ab2ecc57b1dec52d2a7bbf2f4ec3d4a51267029d854a14b0a0ee8"],"state_sha256":"73f2213959420d983a3538c19ff4ec5ba20b38c9f95ee4d2acacfa43b64f1a9d"}