{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4LSIJJ5LEK4FWBK6KCZMPHTJJP","short_pith_number":"pith:4LSIJJ5L","canonical_record":{"source":{"id":"2505.17714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T10:30:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b2066d65efa3d31c17a0e087ff5b6b2fb418cf790c058a5f0f5a32059d386600","abstract_canon_sha256":"50902f7e7967e03e97f117189feaa1d158794e87668718f19e6b7ebc9789c09f"},"schema_version":"1.0"},"canonical_sha256":"e2e484a7ab22b85b055e50b2c79e694bc4d4b0725ee7ddf62a98ada4b61ac7fe","source":{"kind":"arxiv","id":"2505.17714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17714","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17714v1","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17714","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"4LSIJJ5LEK4F","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"4LSIJJ5LEK4FWBK6","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"4LSIJJ5L","created_at":"2026-07-05T11:08:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4LSIJJ5LEK4FWBK6KCZMPHTJJP","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T10:30:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b2066d65efa3d31c17a0e087ff5b6b2fb418cf790c058a5f0f5a32059d386600","abstract_canon_sha256":"50902f7e7967e03e97f117189feaa1d158794e87668718f19e6b7ebc9789c09f"},"schema_version":"1.0"},"canonical_sha256":"e2e484a7ab22b85b055e50b2c79e694bc4d4b0725ee7ddf62a98ada4b61ac7fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:30.716177Z","signature_b64":"Lw7ML81FY4s55N0KxLuhlVqQkqPAvUDON4Y+Jz+44QAaVMSgy+SLRmRDjTqRxOhApeTw9cTlPCQLJucRP/vyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2e484a7ab22b85b055e50b2c79e694bc4d4b0725ee7ddf62a98ada4b61ac7fe","last_reissued_at":"2026-07-05T11:08:30.715720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:30.715720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17714","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":"2026-07-05T11:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"euzOgl15k44xQ6YAanom1yO3FDY3R9AADCTZch2FyDEmPCpsoAsq1ztRu6XnY98VRGi+vdRN4apxzH8gHQiiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:05:01.071166Z"},"content_sha256":"ed02af5b264eaeb52be88a994d927d54dd4be2506ceddc4a7964114edab764fa","schema_version":"1.0","event_id":"sha256:ed02af5b264eaeb52be88a994d927d54dd4be2506ceddc4a7964114edab764fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4LSIJJ5LEK4FWBK6KCZMPHTJJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ben Rahman","submitted_at":"2025-05-23T10:30:58Z","abstract_excerpt":"Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates destabilize convergence. PPO-BR establishes a new paradigm in adaptive RL by fusing exploration and convergence signals into a single bounded trust region -- a theoretically grounded innovation that outperforms five SOTA baselines with less than 2% overhead. This work bridges a critical gap in phase-aware learning, enabling real-world deployment in safety-cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17714","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/2505.17714/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":"2026-07-05T11:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLGDZWpdLuV4RmoKL1RV2eIr7EQMJvp6sYdGErKOwdFIbb2kNsqYFXkMFROD3NMDGID/ecV4+/wQ1CvXVLIaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:05:01.072391Z"},"content_sha256":"07cab99e0d290158d0d6e2220b97f7394574f10cd86ad78c39c9d930c1eeb28d","schema_version":"1.0","event_id":"sha256:07cab99e0d290158d0d6e2220b97f7394574f10cd86ad78c39c9d930c1eeb28d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4LSIJJ5LEK4FWBK6KCZMPHTJJP/bundle.json","state_url":"https://pith.science/pith/4LSIJJ5LEK4FWBK6KCZMPHTJJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4LSIJJ5LEK4FWBK6KCZMPHTJJP/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":"2026-08-18T19:05:01Z","links":{"resolver":"https://pith.science/pith/4LSIJJ5LEK4FWBK6KCZMPHTJJP","bundle":"https://pith.science/pith/4LSIJJ5LEK4FWBK6KCZMPHTJJP/bundle.json","state":"https://pith.science/pith/4LSIJJ5LEK4FWBK6KCZMPHTJJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4LSIJJ5LEK4FWBK6KCZMPHTJJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4LSIJJ5LEK4FWBK6KCZMPHTJJP","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":"50902f7e7967e03e97f117189feaa1d158794e87668718f19e6b7ebc9789c09f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T10:30:58Z","title_canon_sha256":"b2066d65efa3d31c17a0e087ff5b6b2fb418cf790c058a5f0f5a32059d386600"},"schema_version":"1.0","source":{"id":"2505.17714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17714","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17714v1","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17714","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"4LSIJJ5LEK4F","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"4LSIJJ5LEK4FWBK6","created_at":"2026-07-05T11:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"4LSIJJ5L","created_at":"2026-07-05T11:08:30Z"}],"graph_snapshots":[{"event_id":"sha256:07cab99e0d290158d0d6e2220b97f7394574f10cd86ad78c39c9d930c1eeb28d","target":"graph","created_at":"2026-07-05T11:08:30Z","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/2505.17714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates destabilize convergence. PPO-BR establishes a new paradigm in adaptive RL by fusing exploration and convergence signals into a single bounded trust region -- a theoretically grounded innovation that outperforms five SOTA baselines with less than 2% overhead. This work bridges a critical gap in phase-aware learning, enabling real-world deployment in safety-cr","authors_text":"Ben Rahman","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T10:30:58Z","title":"PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17714","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:ed02af5b264eaeb52be88a994d927d54dd4be2506ceddc4a7964114edab764fa","target":"record","created_at":"2026-07-05T11:08:30Z","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":"50902f7e7967e03e97f117189feaa1d158794e87668718f19e6b7ebc9789c09f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T10:30:58Z","title_canon_sha256":"b2066d65efa3d31c17a0e087ff5b6b2fb418cf790c058a5f0f5a32059d386600"},"schema_version":"1.0","source":{"id":"2505.17714","kind":"arxiv","version":1}},"canonical_sha256":"e2e484a7ab22b85b055e50b2c79e694bc4d4b0725ee7ddf62a98ada4b61ac7fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2e484a7ab22b85b055e50b2c79e694bc4d4b0725ee7ddf62a98ada4b61ac7fe","first_computed_at":"2026-07-05T11:08:30.715720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:30.715720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lw7ML81FY4s55N0KxLuhlVqQkqPAvUDON4Y+Jz+44QAaVMSgy+SLRmRDjTqRxOhApeTw9cTlPCQLJucRP/vyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:30.716177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed02af5b264eaeb52be88a994d927d54dd4be2506ceddc4a7964114edab764fa","sha256:07cab99e0d290158d0d6e2220b97f7394574f10cd86ad78c39c9d930c1eeb28d"],"state_sha256":"ecd3fecd82f0f80865a19067f58e13ec07796daf118f051612135633f54bca99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rVA/ymBKLv4P+a41KoYRWdBJazyLaaBgFZmXtiqS/ss65+37AAU8rxRd/55GSnYvmjed9Jx+ZQtn7ZJMrdpBCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:05:01.079515Z","bundle_sha256":"d721bfd7209c484eb0883d58490791bdb8124cd7cb468daff7f0656616c6f722"}}