{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SRQ5EFAEM6LJMOGUJNTLMTFMRC","short_pith_number":"pith:SRQ5EFAE","canonical_record":{"source":{"id":"1807.01672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:40:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"66de93e455004590ba0c3a8ce7358ef1c822921a06e47832b6394f5fadb73cbf","abstract_canon_sha256":"0805f05319c6e2f46b4570add9f3f2ec9a921640d67ce84c2d8326bf7e9e7f8a"},"schema_version":"1.0"},"canonical_sha256":"9461d2140467969638d44b66b64cac8896077b35b9a629bda1c6f987c63a7463","source":{"kind":"arxiv","id":"1807.01672","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01672","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01672v3","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01672","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"pith_short_12","alias_value":"SRQ5EFAEM6LJ","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SRQ5EFAEM6LJMOGU","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SRQ5EFAE","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SRQ5EFAEM6LJMOGUJNTLMTFMRC","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:40:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"66de93e455004590ba0c3a8ce7358ef1c822921a06e47832b6394f5fadb73cbf","abstract_canon_sha256":"0805f05319c6e2f46b4570add9f3f2ec9a921640d67ce84c2d8326bf7e9e7f8a"},"schema_version":"1.0"},"canonical_sha256":"9461d2140467969638d44b66b64cac8896077b35b9a629bda1c6f987c63a7463","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:52.657917Z","signature_b64":"8hbRYGSQcqb20LOGLgibOKwkXQghAgfYNjLhoOMb5eYj3x3u8zoGQ8qCCeSf57dqSP/nK9CjQeZ0xLMWQincDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9461d2140467969638d44b66b64cac8896077b35b9a629bda1c6f987c63a7463","last_reissued_at":"2026-05-17T23:58:52.657302Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:52.657302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01672","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":"2026-05-17T23:58:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rrTTDLo9+OulifVnuGd5p2yzU1h0fxIA/Rb2f1GKnyZSH53GxAw3+ftfAYwrtq8deITNgkAAAN1U5TVeeW+RDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T13:42:40.205959Z"},"content_sha256":"da67edabab9d583cb49c64466d9e3e13127067eace8643a1e2f0fad7ce5bba6c","schema_version":"1.0","event_id":"sha256:da67edabab9d583cb49c64466d9e3e13127067eace8643a1e2f0fad7ce5bba6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SRQ5EFAEM6LJMOGUJNTLMTFMRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain-Sam Cohen, Alexandre Laterre, Amine Kerkeni, David Kas, Karim Beguir, Karl Hajjar, Mohamed Khalil Jabri, Torbjorn S. Dahl, Yunguan Fu","submitted_at":"2018-07-04T16:40:53Z","abstract_excerpt":"Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play training strategy is not directly applicable to single-player games. Recently, several practically important combinatorial optimisation problems, such as the travelling salesman problem and the bin packing problem, have been reformulated as reinforcement learning problems, increas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01672","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":""},"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":"2026-05-17T23:58:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q7t3TxHA7oJpywWkYD1Z4a8gKZOqjQ/VrzuC8hOSuSKBM3HP+vACmhOfR17571A5Pb93WuadeCiv0pPFLbrgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T13:42:40.206680Z"},"content_sha256":"62c2f9368e94371f81f28461aca9a530b58a7081bed706682216cbeb9f828a6c","schema_version":"1.0","event_id":"sha256:62c2f9368e94371f81f28461aca9a530b58a7081bed706682216cbeb9f828a6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/bundle.json","state_url":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/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":"2026-05-25T13:42:40Z","links":{"resolver":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC","bundle":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/bundle.json","state":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SRQ5EFAEM6LJMOGUJNTLMTFMRC","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":"0805f05319c6e2f46b4570add9f3f2ec9a921640d67ce84c2d8326bf7e9e7f8a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:40:53Z","title_canon_sha256":"66de93e455004590ba0c3a8ce7358ef1c822921a06e47832b6394f5fadb73cbf"},"schema_version":"1.0","source":{"id":"1807.01672","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01672","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01672v3","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01672","created_at":"2026-05-17T23:58:52Z"},{"alias_kind":"pith_short_12","alias_value":"SRQ5EFAEM6LJ","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SRQ5EFAEM6LJMOGU","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SRQ5EFAE","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:62c2f9368e94371f81f28461aca9a530b58a7081bed706682216cbeb9f828a6c","target":"graph","created_at":"2026-05-17T23:58:52Z","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"},"paper":{"abstract_excerpt":"Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play training strategy is not directly applicable to single-player games. Recently, several practically important combinatorial optimisation problems, such as the travelling salesman problem and the bin packing problem, have been reformulated as reinforcement learning problems, increas","authors_text":"Alain-Sam Cohen, Alexandre Laterre, Amine Kerkeni, David Kas, Karim Beguir, Karl Hajjar, Mohamed Khalil Jabri, Torbjorn S. Dahl, Yunguan Fu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:40:53Z","title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01672","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:da67edabab9d583cb49c64466d9e3e13127067eace8643a1e2f0fad7ce5bba6c","target":"record","created_at":"2026-05-17T23:58:52Z","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":"0805f05319c6e2f46b4570add9f3f2ec9a921640d67ce84c2d8326bf7e9e7f8a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:40:53Z","title_canon_sha256":"66de93e455004590ba0c3a8ce7358ef1c822921a06e47832b6394f5fadb73cbf"},"schema_version":"1.0","source":{"id":"1807.01672","kind":"arxiv","version":3}},"canonical_sha256":"9461d2140467969638d44b66b64cac8896077b35b9a629bda1c6f987c63a7463","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9461d2140467969638d44b66b64cac8896077b35b9a629bda1c6f987c63a7463","first_computed_at":"2026-05-17T23:58:52.657302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:52.657302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8hbRYGSQcqb20LOGLgibOKwkXQghAgfYNjLhoOMb5eYj3x3u8zoGQ8qCCeSf57dqSP/nK9CjQeZ0xLMWQincDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:52.657917Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01672","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da67edabab9d583cb49c64466d9e3e13127067eace8643a1e2f0fad7ce5bba6c","sha256:62c2f9368e94371f81f28461aca9a530b58a7081bed706682216cbeb9f828a6c"],"state_sha256":"f1db5cd44bfd90abdca7c8db14cac9fc87117055a1c4e738491b88cf9b3533b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iytLF4XGzRtyNkdCK0Vv34CC4BdA9ays4flUvY1j8uIeFvRSojtJp0hGopqWd97M6HQCcm6ozadLu1VOxGeUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T13:42:40.210615Z","bundle_sha256":"16fe22b8d3c35512ebcce3a9373ee5432da265c34400fa59204b8c9616fcb4e2"}}