{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QJX7FKFG35WYRHUMMUMBYRM5CQ","short_pith_number":"pith:QJX7FKFG","canonical_record":{"source":{"id":"2010.16011","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-30T00:57:50Z","cross_cats_sorted":[],"title_canon_sha256":"cff7e9db7096af0a5e1a3341a6066f014d740ef78ee1e251fc87698f1b3710a3","abstract_canon_sha256":"e609fdc38e468fdc840e5986df78d868014d396e6482d23dd2faff090d3e88ef"},"schema_version":"1.0"},"canonical_sha256":"826ff2a8a6df6d889e8c65181c459d14039825e0c23f4ebbbd78adc5020a9495","source":{"kind":"arxiv","id":"2010.16011","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.16011","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"arxiv_version","alias_value":"2010.16011v3","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.16011","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"pith_short_12","alias_value":"QJX7FKFG35WY","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"pith_short_16","alias_value":"QJX7FKFG35WYRHUM","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"pith_short_8","alias_value":"QJX7FKFG","created_at":"2026-07-05T02:57:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QJX7FKFG35WYRHUMMUMBYRM5CQ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.16011","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-30T00:57:50Z","cross_cats_sorted":[],"title_canon_sha256":"cff7e9db7096af0a5e1a3341a6066f014d740ef78ee1e251fc87698f1b3710a3","abstract_canon_sha256":"e609fdc38e468fdc840e5986df78d868014d396e6482d23dd2faff090d3e88ef"},"schema_version":"1.0"},"canonical_sha256":"826ff2a8a6df6d889e8c65181c459d14039825e0c23f4ebbbd78adc5020a9495","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:10.930507Z","signature_b64":"pM5oErB0vf5n2kqGVd95beJohBdFY6ObHD5y2aDtDw4ZjzoadHEt+Mcvt79dxRVJL1wm/8r925xpE9sWoXseAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"826ff2a8a6df6d889e8c65181c459d14039825e0c23f4ebbbd78adc5020a9495","last_reissued_at":"2026-07-05T02:57:10.929989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:10.929989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.16011","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:57:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aB9LnRag6k0SyNGQqKLgPHPvVmpPGTzhtndxnmN2dyieryQu5+2ZypVFvB1Xeys1LwoXTdJNsn+GbKcMU3/LAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:51:47.231676Z"},"content_sha256":"ce695c12fcabef88f9219578fce2b4ee7563536a95b820a931feded19067919a","schema_version":"1.0","event_id":"sha256:ce695c12fcabef88f9219578fce2b4ee7563536a95b820a931feded19067919a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QJX7FKFG35WYRHUMMUMBYRM5CQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byoungjip Kim, Iljoo Yoon, Jinho Choo, Seungjai Min, Yeong-Dae Kwon, Youngjune Gwon","submitted_at":"2020-10-30T00:57:50Z","abstract_excerpt":"In neural combinatorial optimization (CO), reinforcement learning (RL) can turn a deep neural net into a fast, powerful heuristic solver of NP-hard problems. This approach has a great potential in practical applications because it allows near-optimal solutions to be found without expert guides armed with substantial domain knowledge. We introduce Policy Optimization with Multiple Optima (POMO), an end-to-end approach for building such a heuristic solver. POMO is applicable to a wide range of CO problems. It is designed to exploit the symmetries in the representation of a CO solution. POMO uses"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.16011","kind":"arxiv","version":3},"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/2010.16011/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":"2026-07-05T02:57:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qv+ef/NPKLHeFVTiFX4tnX6SXg8XRqe6ckqleZ6uZ1I7M6kPsV/rlMafdnBKPUN41t3vTg/GLCNa1KE5sWbJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:51:47.232516Z"},"content_sha256":"3d59685f865a91de70901dfea6198fe6939571fabc3303ff880b272f6e05e862","schema_version":"1.0","event_id":"sha256:3d59685f865a91de70901dfea6198fe6939571fabc3303ff880b272f6e05e862"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QJX7FKFG35WYRHUMMUMBYRM5CQ/bundle.json","state_url":"https://pith.science/pith/QJX7FKFG35WYRHUMMUMBYRM5CQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QJX7FKFG35WYRHUMMUMBYRM5CQ/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":"2026-08-10T17:51:47Z","links":{"resolver":"https://pith.science/pith/QJX7FKFG35WYRHUMMUMBYRM5CQ","bundle":"https://pith.science/pith/QJX7FKFG35WYRHUMMUMBYRM5CQ/bundle.json","state":"https://pith.science/pith/QJX7FKFG35WYRHUMMUMBYRM5CQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QJX7FKFG35WYRHUMMUMBYRM5CQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QJX7FKFG35WYRHUMMUMBYRM5CQ","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":"e609fdc38e468fdc840e5986df78d868014d396e6482d23dd2faff090d3e88ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-30T00:57:50Z","title_canon_sha256":"cff7e9db7096af0a5e1a3341a6066f014d740ef78ee1e251fc87698f1b3710a3"},"schema_version":"1.0","source":{"id":"2010.16011","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.16011","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"arxiv_version","alias_value":"2010.16011v3","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.16011","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"pith_short_12","alias_value":"QJX7FKFG35WY","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"pith_short_16","alias_value":"QJX7FKFG35WYRHUM","created_at":"2026-07-05T02:57:10Z"},{"alias_kind":"pith_short_8","alias_value":"QJX7FKFG","created_at":"2026-07-05T02:57:10Z"}],"graph_snapshots":[{"event_id":"sha256:3d59685f865a91de70901dfea6198fe6939571fabc3303ff880b272f6e05e862","target":"graph","created_at":"2026-07-05T02:57:10Z","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/2010.16011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In neural combinatorial optimization (CO), reinforcement learning (RL) can turn a deep neural net into a fast, powerful heuristic solver of NP-hard problems. This approach has a great potential in practical applications because it allows near-optimal solutions to be found without expert guides armed with substantial domain knowledge. We introduce Policy Optimization with Multiple Optima (POMO), an end-to-end approach for building such a heuristic solver. POMO is applicable to a wide range of CO problems. It is designed to exploit the symmetries in the representation of a CO solution. POMO uses","authors_text":"Byoungjip Kim, Iljoo Yoon, Jinho Choo, Seungjai Min, Yeong-Dae Kwon, Youngjune Gwon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-30T00:57:50Z","title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.16011","kind":"arxiv","version":3},"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:ce695c12fcabef88f9219578fce2b4ee7563536a95b820a931feded19067919a","target":"record","created_at":"2026-07-05T02:57:10Z","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":"e609fdc38e468fdc840e5986df78d868014d396e6482d23dd2faff090d3e88ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-30T00:57:50Z","title_canon_sha256":"cff7e9db7096af0a5e1a3341a6066f014d740ef78ee1e251fc87698f1b3710a3"},"schema_version":"1.0","source":{"id":"2010.16011","kind":"arxiv","version":3}},"canonical_sha256":"826ff2a8a6df6d889e8c65181c459d14039825e0c23f4ebbbd78adc5020a9495","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"826ff2a8a6df6d889e8c65181c459d14039825e0c23f4ebbbd78adc5020a9495","first_computed_at":"2026-07-05T02:57:10.929989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:57:10.929989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pM5oErB0vf5n2kqGVd95beJohBdFY6ObHD5y2aDtDw4ZjzoadHEt+Mcvt79dxRVJL1wm/8r925xpE9sWoXseAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:57:10.930507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.16011","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce695c12fcabef88f9219578fce2b4ee7563536a95b820a931feded19067919a","sha256:3d59685f865a91de70901dfea6198fe6939571fabc3303ff880b272f6e05e862"],"state_sha256":"1a7bc4f184473c680666ddedf4566bdcd2b8df4d4af79c07606064339d11c140"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v4IuBpWKkBnWcubpQNhlJFFB4B+lbXTr1F4uDxv3i/lMHNUUliTSPrBiFFCNDqql4w8Ut1Skb412aPufUQw2Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:51:47.238536Z","bundle_sha256":"1fe8bc63371b0801f40c614d3882ff37a8525058a25bdc1f96c32eca64721cf8"}}