{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4MHGVD6XTW2WL5MDVON2E56EE7","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":"9517ae5873ac93c95187f1676cb8d1728316a8c905e568982f01ba53661afb46","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T12:40:22Z","title_canon_sha256":"760400c9737ed52fdd60eaff456f27b525f94f56c826480947450ac3f9aa18f5"},"schema_version":"1.0","source":{"id":"2605.29860","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29860","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29860v1","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29860","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"4MHGVD6XTW2W","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"4MHGVD6XTW2WL5MD","created_at":"2026-05-29T02:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"4MHGVD6X","created_at":"2026-05-29T02:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:c3a086373cd7469e6aaee5c98ee88f48f59d1be5c68f269b4ac8518c3105c391","target":"graph","created_at":"2026-05-29T02:05:56Z","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/2605.29860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When a large language model under reinforcement learning commits a wrong reasoning step early in a trajectory, standard algorithms force it to keep generating until the maximum horizon, spending compute on tokens that never receive positive reward and polluting advantage estimates with post-failure noise. We propose ESPO (Early-Stopping Proximal Policy Optimization), which detects trajectory failure on-the-fly and terminates rollouts early. At each generation step, ESPO computes a surrogate regret using only the logits already computed during sampling, and terminates when the smoothed cumulati","authors_text":"Binhua Li, Jieping Ye, Rui Zhou, Tong Yang, Wenhan Yu, Yingcheng Shi, Yongbin Li, Zeming Li, Zhewen Tan, Zihang Li, Zixiang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T12:40:22Z","title":"ESPO: Early-Stopping Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29860","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":"sha256:0a9b30f2732ccbec462b52c854a1e24f43dd89c23cc062b22ceb05fa08febec7","target":"record","created_at":"2026-05-29T02:05:56Z","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":"9517ae5873ac93c95187f1676cb8d1728316a8c905e568982f01ba53661afb46","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T12:40:22Z","title_canon_sha256":"760400c9737ed52fdd60eaff456f27b525f94f56c826480947450ac3f9aa18f5"},"schema_version":"1.0","source":{"id":"2605.29860","kind":"arxiv","version":1}},"canonical_sha256":"e30e6a8fd79db565f583ab9ba277c427daa1f8a57e062a0b075b7ac6bd042c17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e30e6a8fd79db565f583ab9ba277c427daa1f8a57e062a0b075b7ac6bd042c17","first_computed_at":"2026-05-29T02:05:56.557375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:56.557375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f/TDiExwKTngQidq0w5L8OHWeFobmdm08jLP+YHUysZI2B/D69i6zOvfZs0xhi8bVSE370j39KLy0nbDbWVSDA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:56.557999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29860","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a9b30f2732ccbec462b52c854a1e24f43dd89c23cc062b22ceb05fa08febec7","sha256:c3a086373cd7469e6aaee5c98ee88f48f59d1be5c68f269b4ac8518c3105c391"],"state_sha256":"a70707857134240d2560d4d274278a2b530ad17bd23272af883b0aae1ebf5f7d"}