{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KTKWJYVUGNDJ55YMH26YNRZN6U","short_pith_number":"pith:KTKWJYVU","canonical_record":{"source":{"id":"2307.00783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-03T07:01:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c24a1affb239a505623882874abddfb56a0f1b28323bb5add61abe4909a7979e","abstract_canon_sha256":"eecdc0d9ced17cef321dd2a47bd9d10ab1b5d0de0c973425f3c322dee465ef72"},"schema_version":"1.0"},"canonical_sha256":"54d564e2b433469ef70c3ebd86c72df518df321c57bd8777c72dfdd250d7ff94","source":{"kind":"arxiv","id":"2307.00783","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00783","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00783v1","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00783","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_12","alias_value":"KTKWJYVUGNDJ","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_16","alias_value":"KTKWJYVUGNDJ55YM","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_8","alias_value":"KTKWJYVU","created_at":"2026-07-05T06:27:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KTKWJYVUGNDJ55YMH26YNRZN6U","target":"record","payload":{"canonical_record":{"source":{"id":"2307.00783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-03T07:01:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c24a1affb239a505623882874abddfb56a0f1b28323bb5add61abe4909a7979e","abstract_canon_sha256":"eecdc0d9ced17cef321dd2a47bd9d10ab1b5d0de0c973425f3c322dee465ef72"},"schema_version":"1.0"},"canonical_sha256":"54d564e2b433469ef70c3ebd86c72df518df321c57bd8777c72dfdd250d7ff94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:00.467149Z","signature_b64":"Frz113JhDxReLN22GqLZoVK1mu/SLCMuwHiyKVkTngyHS/Lq6yEjYYSsM2oS2zs1HIHkohNL8IN5vOL5X1afCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d564e2b433469ef70c3ebd86c72df518df321c57bd8777c72dfdd250d7ff94","last_reissued_at":"2026-07-05T06:27:00.466687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:00.466687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.00783","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":"2026-07-05T06:27:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"39eOwM1HjSdEtuVRq/Hf/p7GSvxPQMsZtGWNuG3i5nIwzWq7NvYbr8z3+zHk39mQP6i8Irgk3CDK6VxgjA84Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:15:57.262950Z"},"content_sha256":"4eff6516abcfbac4b75208f84e7245e3c1b4638fad3d4812a7e63d40ff8c7089","schema_version":"1.0","event_id":"sha256:4eff6516abcfbac4b75208f84e7245e3c1b4638fad3d4812a7e63d40ff8c7089"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KTKWJYVUGNDJ55YMH26YNRZN6U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Monte Carlo Policy Gradient Method for Binary Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"math.OC","authors_text":"Cheng Chen, Ruichen Ao, Ruitao Chen, Tianyou Li, Zaiwen Wen","submitted_at":"2023-07-03T07:01:42Z","abstract_excerpt":"Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT. However, these problems are typically NP-hard due to the binary constraints. We develop a novel probabilistic model to sample the binary solution according to a parameterized policy distribution. Specifically, minimizing the KL divergence between the parameterized policy distribution and the Gibbs distributions of the function value leads to a stochastic optimization problem whose policy gradient can be derived explicitly similar to reinforcement learning. For"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00783","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/2307.00783/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":"2026-07-05T06:27:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXeE3R8ous40bcUnwH7gXLPfzSPs1Hq4STjAZWf/E18RIy8f5iY42Eiwn2ao05jHIcrJjDIXOuy5hPQDDTXUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:15:57.263454Z"},"content_sha256":"d85bfc638a557ea7ff4aaaf643910e09e4953d9812c97489b838640bc9fd343d","schema_version":"1.0","event_id":"sha256:d85bfc638a557ea7ff4aaaf643910e09e4953d9812c97489b838640bc9fd343d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/bundle.json","state_url":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/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":"2026-08-19T20:15:57Z","links":{"resolver":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U","bundle":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/bundle.json","state":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KTKWJYVUGNDJ55YMH26YNRZN6U","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":"eecdc0d9ced17cef321dd2a47bd9d10ab1b5d0de0c973425f3c322dee465ef72","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-03T07:01:42Z","title_canon_sha256":"c24a1affb239a505623882874abddfb56a0f1b28323bb5add61abe4909a7979e"},"schema_version":"1.0","source":{"id":"2307.00783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00783","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00783v1","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00783","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_12","alias_value":"KTKWJYVUGNDJ","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_16","alias_value":"KTKWJYVUGNDJ55YM","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_8","alias_value":"KTKWJYVU","created_at":"2026-07-05T06:27:00Z"}],"graph_snapshots":[{"event_id":"sha256:d85bfc638a557ea7ff4aaaf643910e09e4953d9812c97489b838640bc9fd343d","target":"graph","created_at":"2026-07-05T06:27:00Z","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/2307.00783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT. However, these problems are typically NP-hard due to the binary constraints. We develop a novel probabilistic model to sample the binary solution according to a parameterized policy distribution. Specifically, minimizing the KL divergence between the parameterized policy distribution and the Gibbs distributions of the function value leads to a stochastic optimization problem whose policy gradient can be derived explicitly similar to reinforcement learning. For","authors_text":"Cheng Chen, Ruichen Ao, Ruitao Chen, Tianyou Li, Zaiwen Wen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-03T07:01:42Z","title":"Monte Carlo Policy Gradient Method for Binary Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00783","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":"sha256:4eff6516abcfbac4b75208f84e7245e3c1b4638fad3d4812a7e63d40ff8c7089","target":"record","created_at":"2026-07-05T06:27:00Z","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":"eecdc0d9ced17cef321dd2a47bd9d10ab1b5d0de0c973425f3c322dee465ef72","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-03T07:01:42Z","title_canon_sha256":"c24a1affb239a505623882874abddfb56a0f1b28323bb5add61abe4909a7979e"},"schema_version":"1.0","source":{"id":"2307.00783","kind":"arxiv","version":1}},"canonical_sha256":"54d564e2b433469ef70c3ebd86c72df518df321c57bd8777c72dfdd250d7ff94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54d564e2b433469ef70c3ebd86c72df518df321c57bd8777c72dfdd250d7ff94","first_computed_at":"2026-07-05T06:27:00.466687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:27:00.466687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Frz113JhDxReLN22GqLZoVK1mu/SLCMuwHiyKVkTngyHS/Lq6yEjYYSsM2oS2zs1HIHkohNL8IN5vOL5X1afCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:27:00.467149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4eff6516abcfbac4b75208f84e7245e3c1b4638fad3d4812a7e63d40ff8c7089","sha256:d85bfc638a557ea7ff4aaaf643910e09e4953d9812c97489b838640bc9fd343d"],"state_sha256":"92f6cce6452b7599a0bb0b1c82f447449bc02b185bb5c533eff3b9e3b0ff90ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gbSDcnj3i60ewlQ18Tg2+gpO97gt8UNIcE9SH7hSMb6vUAu0GTFk54IOJpeUSrQP64fy2mG46BdFUjy1LEElDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:15:57.268346Z","bundle_sha256":"d6e93d62f3d73eb5aa9d75c5acfc9a8f50b445b68908459ac5a89968950a3753"}}