{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:V2CEMBS5MUCCRFJWLPFITLSS7U","short_pith_number":"pith:V2CEMBS5","canonical_record":{"source":{"id":"2312.08710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T07:50:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4fc6883232ec4b811191217f648bd195ccb524ed9c8b17af2b34430143b3746","abstract_canon_sha256":"681129e3f42cca74b4bf1aed179d52b312c81221b0da7c1fc56e6828fea984ac"},"schema_version":"1.0"},"canonical_sha256":"ae8446065d65042895365bca89ae52fd3e7e910a7a0aed6e44c8f708e4685e68","source":{"kind":"arxiv","id":"2312.08710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08710","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08710v1","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08710","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"V2CEMBS5MUCC","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"V2CEMBS5MUCCRFJW","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"V2CEMBS5","created_at":"2026-07-05T07:24:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:V2CEMBS5MUCCRFJWLPFITLSS7U","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T07:50:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4fc6883232ec4b811191217f648bd195ccb524ed9c8b17af2b34430143b3746","abstract_canon_sha256":"681129e3f42cca74b4bf1aed179d52b312c81221b0da7c1fc56e6828fea984ac"},"schema_version":"1.0"},"canonical_sha256":"ae8446065d65042895365bca89ae52fd3e7e910a7a0aed6e44c8f708e4685e68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:08.391637Z","signature_b64":"varcyU8gNzVI7DG3oUGFiGd76w1SBvOBdTggNwVkfrQaMlv88Na9TsiFqFU5guzVqeSjS3HvrXA1Wkpp09LJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae8446065d65042895365bca89ae52fd3e7e910a7a0aed6e44c8f708e4685e68","last_reissued_at":"2026-07-05T07:24:08.390926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:08.390926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08710","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":"2026-07-05T07:24:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQQmunKDCYH+FfBdyWvNJ93iw0li52vkhOlPtuCwg7tpsXtdXkJAwLFP6FEtyXbmzK+I191y6FLnInnzUSGjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:42:26.682744Z"},"content_sha256":"8d433573d8f22339850248c50cadcfde9668bb09a700f28820955414198d971a","schema_version":"1.0","event_id":"sha256:8d433573d8f22339850248c50cadcfde9668bb09a700f28820955414198d971a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:V2CEMBS5MUCCRFJWLPFITLSS7U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient Informed Proximal Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Laura Yu Zheng, Ming C. Lin, Ryan Sullivan, Sanghyun Son, Yi-Ling Qiao","submitted_at":"2023-12-14T07:50:21Z","abstract_excerpt":"We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we introduce the concept of an {\\alpha}-policy that stands as a locally superior policy. By adaptively modifying the {\\alpha} value, we can effectively manage the influence of analytical policy gradients during learning. To this end, we suggest metrics for assessing the variance and bias of analytical gradients, reducing dependence on these gradients when high variance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08710","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/2312.08710/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":"2026-07-05T07:24:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRrgrUF/4Pvgzwgv1tpQriPCkwXuUic8fWQ0unrwU3WnodSoRzCBCdM5V2+B8t0vmGVU9CqsJ5L0/dieDcnuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:42:26.683120Z"},"content_sha256":"a7d79bfd03383d796405129bbc384df296462783c93c246d3ba300202856903f","schema_version":"1.0","event_id":"sha256:a7d79bfd03383d796405129bbc384df296462783c93c246d3ba300202856903f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V2CEMBS5MUCCRFJWLPFITLSS7U/bundle.json","state_url":"https://pith.science/pith/V2CEMBS5MUCCRFJWLPFITLSS7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V2CEMBS5MUCCRFJWLPFITLSS7U/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":"2026-07-06T11:42:26Z","links":{"resolver":"https://pith.science/pith/V2CEMBS5MUCCRFJWLPFITLSS7U","bundle":"https://pith.science/pith/V2CEMBS5MUCCRFJWLPFITLSS7U/bundle.json","state":"https://pith.science/pith/V2CEMBS5MUCCRFJWLPFITLSS7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V2CEMBS5MUCCRFJWLPFITLSS7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V2CEMBS5MUCCRFJWLPFITLSS7U","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":"681129e3f42cca74b4bf1aed179d52b312c81221b0da7c1fc56e6828fea984ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T07:50:21Z","title_canon_sha256":"a4fc6883232ec4b811191217f648bd195ccb524ed9c8b17af2b34430143b3746"},"schema_version":"1.0","source":{"id":"2312.08710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08710","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08710v1","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08710","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"V2CEMBS5MUCC","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"V2CEMBS5MUCCRFJW","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"V2CEMBS5","created_at":"2026-07-05T07:24:08Z"}],"graph_snapshots":[{"event_id":"sha256:a7d79bfd03383d796405129bbc384df296462783c93c246d3ba300202856903f","target":"graph","created_at":"2026-07-05T07:24:08Z","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/2312.08710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we introduce the concept of an {\\alpha}-policy that stands as a locally superior policy. By adaptively modifying the {\\alpha} value, we can effectively manage the influence of analytical policy gradients during learning. To this end, we suggest metrics for assessing the variance and bias of analytical gradients, reducing dependence on these gradients when high variance","authors_text":"Laura Yu Zheng, Ming C. Lin, Ryan Sullivan, Sanghyun Son, Yi-Ling Qiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T07:50:21Z","title":"Gradient Informed Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08710","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":"sha256:8d433573d8f22339850248c50cadcfde9668bb09a700f28820955414198d971a","target":"record","created_at":"2026-07-05T07:24:08Z","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":"681129e3f42cca74b4bf1aed179d52b312c81221b0da7c1fc56e6828fea984ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T07:50:21Z","title_canon_sha256":"a4fc6883232ec4b811191217f648bd195ccb524ed9c8b17af2b34430143b3746"},"schema_version":"1.0","source":{"id":"2312.08710","kind":"arxiv","version":1}},"canonical_sha256":"ae8446065d65042895365bca89ae52fd3e7e910a7a0aed6e44c8f708e4685e68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae8446065d65042895365bca89ae52fd3e7e910a7a0aed6e44c8f708e4685e68","first_computed_at":"2026-07-05T07:24:08.390926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:08.390926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"varcyU8gNzVI7DG3oUGFiGd76w1SBvOBdTggNwVkfrQaMlv88Na9TsiFqFU5guzVqeSjS3HvrXA1Wkpp09LJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:08.391637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d433573d8f22339850248c50cadcfde9668bb09a700f28820955414198d971a","sha256:a7d79bfd03383d796405129bbc384df296462783c93c246d3ba300202856903f"],"state_sha256":"a1c5fb10ec8de1d0ba5effa9390c876f9d796d99161441249bfbdbfff42d09be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rmaEd5jIiuHU8vmfGGsU5wC5VjVch3aCHM1NakF7XepjkcOXwU/tMfkMpxsCkqyeOCFLs+zU2f9J0OYuE8kyAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T11:42:26.685178Z","bundle_sha256":"5a9c232d05c64f5ed18556a0663fc2cba776621aa6f0fab9e21da218f0542ab2"}}