{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:26RNVLS7K2SD6ACQHTTEPHVXGX","short_pith_number":"pith:26RNVLS7","canonical_record":{"source":{"id":"2405.17832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T05:05:33Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f2f853ef986f58ed7fc2653e6a3801c0729bd6ea8c5589fb6241adb92078d8f9","abstract_canon_sha256":"643743067a61b93b93a0221955b2788d578f05d52817aec741cd4822bdb09952"},"schema_version":"1.0"},"canonical_sha256":"d7a2daae5f56a43f00503ce6479eb735c4305699372907f8a289cebc39822f38","source":{"kind":"arxiv","id":"2405.17832","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17832","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17832v1","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17832","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"pith_short_12","alias_value":"26RNVLS7K2SD","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"pith_short_16","alias_value":"26RNVLS7K2SD6ACQ","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"pith_short_8","alias_value":"26RNVLS7","created_at":"2026-07-05T08:24:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:26RNVLS7K2SD6ACQHTTEPHVXGX","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T05:05:33Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f2f853ef986f58ed7fc2653e6a3801c0729bd6ea8c5589fb6241adb92078d8f9","abstract_canon_sha256":"643743067a61b93b93a0221955b2788d578f05d52817aec741cd4822bdb09952"},"schema_version":"1.0"},"canonical_sha256":"d7a2daae5f56a43f00503ce6479eb735c4305699372907f8a289cebc39822f38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:11.954590Z","signature_b64":"vZNvaAFCH2WMFD70PTlaw6oMxLpmbCKdoI5vSWm1gR57ORveQQkMaE53hg3o4uYn06C6dArWu4S8DuIZ0Py5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7a2daae5f56a43f00503ce6479eb735c4305699372907f8a289cebc39822f38","last_reissued_at":"2026-07-05T08:24:11.954170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:11.954170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17832","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":"2026-07-05T08:24:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3bMG2lFhartepFpA8Zn+W0+wg3U1gbVMN1grz5vM7jgRfROYr+M/QjZnaFCqPUg4YnHFDQKcycyLupW6RXNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:44:41.714378Z"},"content_sha256":"1ebab04ecf0417925dff119af11a9e7f4b5b72850f2ea8490fb236d5e867aae2","schema_version":"1.0","event_id":"sha256:1ebab04ecf0417925dff119af11a9e7f4b5b72850f2ea8490fb236d5e867aae2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:26RNVLS7K2SD6ACQHTTEPHVXGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mollification Effects of Policy Gradient Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Sicun Gao, Sylvia Herbert, Tao Wang","submitted_at":"2024-05-28T05:05:33Z","abstract_excerpt":"Policy gradient methods have enabled deep reinforcement learning (RL) to approach challenging continuous control problems, even when the underlying systems involve highly nonlinear dynamics that generate complex non-smooth optimization landscapes. We develop a rigorous framework for understanding how policy gradient methods mollify non-smooth optimization landscapes to enable effective policy search, as well as the downside of it: while making the objective function smoother and easier to optimize, the stochastic objective deviates further from the original problem. We demonstrate the equivale"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17832","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/2405.17832/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":"2026-07-05T08:24:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yzw65LeosvhF7Z7woPAXfQR0SSLWsdBJoLcX5dEcAS47OXzlhL6D8Nvl375aehUHxJaItlvRsD+T9Oip4GU+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:44:41.714883Z"},"content_sha256":"c803c5865edc9384ccf6595526e7447cddc4414fb26c2bc375727011855baf47","schema_version":"1.0","event_id":"sha256:c803c5865edc9384ccf6595526e7447cddc4414fb26c2bc375727011855baf47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/bundle.json","state_url":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/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":"2026-08-06T17:44:41Z","links":{"resolver":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX","bundle":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/bundle.json","state":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:26RNVLS7K2SD6ACQHTTEPHVXGX","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":"643743067a61b93b93a0221955b2788d578f05d52817aec741cd4822bdb09952","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T05:05:33Z","title_canon_sha256":"f2f853ef986f58ed7fc2653e6a3801c0729bd6ea8c5589fb6241adb92078d8f9"},"schema_version":"1.0","source":{"id":"2405.17832","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17832","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17832v1","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17832","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"pith_short_12","alias_value":"26RNVLS7K2SD","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"pith_short_16","alias_value":"26RNVLS7K2SD6ACQ","created_at":"2026-07-05T08:24:11Z"},{"alias_kind":"pith_short_8","alias_value":"26RNVLS7","created_at":"2026-07-05T08:24:11Z"}],"graph_snapshots":[{"event_id":"sha256:c803c5865edc9384ccf6595526e7447cddc4414fb26c2bc375727011855baf47","target":"graph","created_at":"2026-07-05T08:24:11Z","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/2405.17832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient methods have enabled deep reinforcement learning (RL) to approach challenging continuous control problems, even when the underlying systems involve highly nonlinear dynamics that generate complex non-smooth optimization landscapes. We develop a rigorous framework for understanding how policy gradient methods mollify non-smooth optimization landscapes to enable effective policy search, as well as the downside of it: while making the objective function smoother and easier to optimize, the stochastic objective deviates further from the original problem. We demonstrate the equivale","authors_text":"Sicun Gao, Sylvia Herbert, Tao Wang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T05:05:33Z","title":"Mollification Effects of Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17832","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":"sha256:1ebab04ecf0417925dff119af11a9e7f4b5b72850f2ea8490fb236d5e867aae2","target":"record","created_at":"2026-07-05T08:24:11Z","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":"643743067a61b93b93a0221955b2788d578f05d52817aec741cd4822bdb09952","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T05:05:33Z","title_canon_sha256":"f2f853ef986f58ed7fc2653e6a3801c0729bd6ea8c5589fb6241adb92078d8f9"},"schema_version":"1.0","source":{"id":"2405.17832","kind":"arxiv","version":1}},"canonical_sha256":"d7a2daae5f56a43f00503ce6479eb735c4305699372907f8a289cebc39822f38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7a2daae5f56a43f00503ce6479eb735c4305699372907f8a289cebc39822f38","first_computed_at":"2026-07-05T08:24:11.954170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:11.954170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vZNvaAFCH2WMFD70PTlaw6oMxLpmbCKdoI5vSWm1gR57ORveQQkMaE53hg3o4uYn06C6dArWu4S8DuIZ0Py5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:11.954590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17832","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ebab04ecf0417925dff119af11a9e7f4b5b72850f2ea8490fb236d5e867aae2","sha256:c803c5865edc9384ccf6595526e7447cddc4414fb26c2bc375727011855baf47"],"state_sha256":"63d5613f6e30e52d1eb0bbb190830381b2e731fb2b1699b92f2e8f9833485e37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LZ+2HOvKwcupz7qEn9iTNQ0tqsgI+K5Nbg6q5gmHqGHLg5Ie2SZjzScMEjshbGJ1ttyAmlFVAFgyhYeuxyEoCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:44:41.720337Z","bundle_sha256":"4b26ef8c3fa2209e14587a8c414347bc413520f367833ea84de7ea5ef84b7712"}}