{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GSHFY3LCOWJF4INGSR43ZSXWAL","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":"63481111f784cfb509929de9c97a3f50ae5a3dd28aaf9f7447ea353700f52ec2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T11:33:18Z","title_canon_sha256":"1e0166455fe9bd14b020005b07fc5ddaa694eda70673194f961c2106c14fa951"},"schema_version":"1.0","source":{"id":"2312.12065","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12065","created_at":"2026-07-05T07:46:28Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12065v2","created_at":"2026-07-05T07:46:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12065","created_at":"2026-07-05T07:46:28Z"},{"alias_kind":"pith_short_12","alias_value":"GSHFY3LCOWJF","created_at":"2026-07-05T07:46:28Z"},{"alias_kind":"pith_short_16","alias_value":"GSHFY3LCOWJF4ING","created_at":"2026-07-05T07:46:28Z"},{"alias_kind":"pith_short_8","alias_value":"GSHFY3LC","created_at":"2026-07-05T07:46:28Z"}],"graph_snapshots":[{"event_id":"sha256:da32441e753492b30d11797a7f55503df22e5dde3b9b02b55855e5416f7cf562","target":"graph","created_at":"2026-07-05T07:46:28Z","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/2312.12065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proximal Policy Optimization algorithm employing a clipped surrogate objective (PPO-Clip) is a prominent exemplar of the policy optimization methods. However, despite its remarkable empirical success, PPO-Clip lacks theoretical substantiation to date. In this paper, we contribute to the field by establishing the first global convergence results of a PPO-Clip variant in both tabular and neural function approximation settings. Our findings highlight the $O(1/\\sqrt{T})$ min-iterate convergence rate specifically in the context of neural function approximation. We tackle the inherent challenges in ","authors_text":"I-Chen Wu, Kuo-Hao Ho, Nai-Chieh Huang, Ping-Chun Hsieh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T11:33:18Z","title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12065","kind":"arxiv","version":2},"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:d9aa1ead09c9bfa141bc60c71b08911488d537253048079dbb7c9931ad721d72","target":"record","created_at":"2026-07-05T07:46:28Z","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":"63481111f784cfb509929de9c97a3f50ae5a3dd28aaf9f7447ea353700f52ec2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T11:33:18Z","title_canon_sha256":"1e0166455fe9bd14b020005b07fc5ddaa694eda70673194f961c2106c14fa951"},"schema_version":"1.0","source":{"id":"2312.12065","kind":"arxiv","version":2}},"canonical_sha256":"348e5c6d6275925e21a69479bccaf602db2da6512734bd4acfcbc4f4657db8b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"348e5c6d6275925e21a69479bccaf602db2da6512734bd4acfcbc4f4657db8b4","first_computed_at":"2026-07-05T07:46:28.997289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:28.997289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CUZ8ZkbVSbNMtPvTz4/6SQIusG6nDUz9AfujTQTqJnJdXPyNyh3PKQiPaoAwFvH0/FIGST3KpWW5ZXBjrZxBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:28.997849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12065","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9aa1ead09c9bfa141bc60c71b08911488d537253048079dbb7c9931ad721d72","sha256:da32441e753492b30d11797a7f55503df22e5dde3b9b02b55855e5416f7cf562"],"state_sha256":"8bf24e999d730ee119838f63fb9fa160437e5990e73f65a28879c37c476cc33f"}