{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4Z4IFJ7UEA6Q3PSK57QXYYWA3P","short_pith_number":"pith:4Z4IFJ7U","canonical_record":{"source":{"id":"2506.14460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T12:20:04Z","cross_cats_sorted":[],"title_canon_sha256":"9e1d9e67271992f4b5309a1b7ca8c52348e5ae7e059171dc9bd11981d142e846","abstract_canon_sha256":"102728fb5a1cf9a85fe4de577c287b63b3680416e8ac7bd19de5689c55361ff6"},"schema_version":"1.0"},"canonical_sha256":"e67882a7f4203d0dbe4aefe17c62c0dbe1f6757c12dde5cfce91f739044cab85","source":{"kind":"arxiv","id":"2506.14460","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14460","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14460v1","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14460","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_12","alias_value":"4Z4IFJ7UEA6Q","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_16","alias_value":"4Z4IFJ7UEA6Q3PSK","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_8","alias_value":"4Z4IFJ7U","created_at":"2026-07-05T11:22:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4Z4IFJ7UEA6Q3PSK57QXYYWA3P","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T12:20:04Z","cross_cats_sorted":[],"title_canon_sha256":"9e1d9e67271992f4b5309a1b7ca8c52348e5ae7e059171dc9bd11981d142e846","abstract_canon_sha256":"102728fb5a1cf9a85fe4de577c287b63b3680416e8ac7bd19de5689c55361ff6"},"schema_version":"1.0"},"canonical_sha256":"e67882a7f4203d0dbe4aefe17c62c0dbe1f6757c12dde5cfce91f739044cab85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:56.975296Z","signature_b64":"HsB3Cn1deO9v/kXcj2pXEIbWUVMJoomxZTkQLn2adCNeeV+GGccXU8Ek6aXPiNyrpSJLCG7xS/oiFdy+6+5xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e67882a7f4203d0dbe4aefe17c62c0dbe1f6757c12dde5cfce91f739044cab85","last_reissued_at":"2026-07-05T11:22:56.974839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:56.974839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14460","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":"2026-07-05T11:22:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALEaby/3cJjaDExz/LsEpORr3RQ8c32JNdyZcCSeggrGpfZNonsHaA2ZA6B+UUJZXb1V+cer55R7vwEwa7ntAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:17:57.613735Z"},"content_sha256":"74b1be229546cacb41858dbbc3cba439337c3ba7dbe49280e8011113b7334a49","schema_version":"1.0","event_id":"sha256:74b1be229546cacb41858dbbc3cba439337c3ba7dbe49280e8011113b7334a49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4Z4IFJ7UEA6Q3PSK57QXYYWA3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zeroth-Order Optimization is Secretly Single-Step Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junbin Qiu, Xiangda Yan, Yao Shu, Yongjie Yang, Zhengpeng Xie","submitted_at":"2025-06-17T12:20:04Z","abstract_excerpt":"Zeroth-Order Optimization (ZOO) provides powerful tools for optimizing functions where explicit gradients are unavailable or expensive to compute. However, the underlying mechanisms of popular ZOO methods, particularly those employing randomized finite differences, and their connection to other optimization paradigms like Reinforcement Learning (RL) are not fully elucidated. This paper establishes a fundamental and previously unrecognized connection: ZOO with finite differences is equivalent to a specific instance of single-step Policy Optimization (PO). We formally unveil that the implicitly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14460","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/2506.14460/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":"2026-07-05T11:22:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qm8iu/66JSOdhUFO5iTxsE9TmrZMOizOJKdQBhTTU6ZlJiYrZhXW1OcdgoAjbrZSzwZRgvUdR6rxr+1ofM45DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:17:57.614075Z"},"content_sha256":"1e5d53c45371d8441ff88a786fa7d6c0cdfe7e0fd24139bbf7dc64f8b581e879","schema_version":"1.0","event_id":"sha256:1e5d53c45371d8441ff88a786fa7d6c0cdfe7e0fd24139bbf7dc64f8b581e879"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4Z4IFJ7UEA6Q3PSK57QXYYWA3P/bundle.json","state_url":"https://pith.science/pith/4Z4IFJ7UEA6Q3PSK57QXYYWA3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4Z4IFJ7UEA6Q3PSK57QXYYWA3P/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":"2026-08-21T08:17:57Z","links":{"resolver":"https://pith.science/pith/4Z4IFJ7UEA6Q3PSK57QXYYWA3P","bundle":"https://pith.science/pith/4Z4IFJ7UEA6Q3PSK57QXYYWA3P/bundle.json","state":"https://pith.science/pith/4Z4IFJ7UEA6Q3PSK57QXYYWA3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4Z4IFJ7UEA6Q3PSK57QXYYWA3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4Z4IFJ7UEA6Q3PSK57QXYYWA3P","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":"102728fb5a1cf9a85fe4de577c287b63b3680416e8ac7bd19de5689c55361ff6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T12:20:04Z","title_canon_sha256":"9e1d9e67271992f4b5309a1b7ca8c52348e5ae7e059171dc9bd11981d142e846"},"schema_version":"1.0","source":{"id":"2506.14460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14460","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14460v1","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14460","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_12","alias_value":"4Z4IFJ7UEA6Q","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_16","alias_value":"4Z4IFJ7UEA6Q3PSK","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_8","alias_value":"4Z4IFJ7U","created_at":"2026-07-05T11:22:56Z"}],"graph_snapshots":[{"event_id":"sha256:1e5d53c45371d8441ff88a786fa7d6c0cdfe7e0fd24139bbf7dc64f8b581e879","target":"graph","created_at":"2026-07-05T11:22:56Z","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/2506.14460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zeroth-Order Optimization (ZOO) provides powerful tools for optimizing functions where explicit gradients are unavailable or expensive to compute. However, the underlying mechanisms of popular ZOO methods, particularly those employing randomized finite differences, and their connection to other optimization paradigms like Reinforcement Learning (RL) are not fully elucidated. This paper establishes a fundamental and previously unrecognized connection: ZOO with finite differences is equivalent to a specific instance of single-step Policy Optimization (PO). We formally unveil that the implicitly ","authors_text":"Junbin Qiu, Xiangda Yan, Yao Shu, Yongjie Yang, Zhengpeng Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T12:20:04Z","title":"Zeroth-Order Optimization is Secretly Single-Step Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14460","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":"sha256:74b1be229546cacb41858dbbc3cba439337c3ba7dbe49280e8011113b7334a49","target":"record","created_at":"2026-07-05T11:22:56Z","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":"102728fb5a1cf9a85fe4de577c287b63b3680416e8ac7bd19de5689c55361ff6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T12:20:04Z","title_canon_sha256":"9e1d9e67271992f4b5309a1b7ca8c52348e5ae7e059171dc9bd11981d142e846"},"schema_version":"1.0","source":{"id":"2506.14460","kind":"arxiv","version":1}},"canonical_sha256":"e67882a7f4203d0dbe4aefe17c62c0dbe1f6757c12dde5cfce91f739044cab85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e67882a7f4203d0dbe4aefe17c62c0dbe1f6757c12dde5cfce91f739044cab85","first_computed_at":"2026-07-05T11:22:56.974839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:56.974839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HsB3Cn1deO9v/kXcj2pXEIbWUVMJoomxZTkQLn2adCNeeV+GGccXU8Ek6aXPiNyrpSJLCG7xS/oiFdy+6+5xBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:56.975296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74b1be229546cacb41858dbbc3cba439337c3ba7dbe49280e8011113b7334a49","sha256:1e5d53c45371d8441ff88a786fa7d6c0cdfe7e0fd24139bbf7dc64f8b581e879"],"state_sha256":"f17a5704b43baf3b915a84d5d61bcfcb0ab02be2e05dbbb0cab8c8634870b529"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"57TsS3R2gF2MlE3KeHiSS83u88tvULtgZVyBYB3uivYNCtJzkr4wsAVNvp6Xs7SFOjQILqYREyVqAA55MQlfAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T08:17:57.617246Z","bundle_sha256":"01be78d45fbb4dd9623012f7fd2eb3bfa71d20e9f9f11f8ba5a7623398fe92be"}}