{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XKHH25KNNKDBYEDBWZWW4DKNKV","short_pith_number":"pith:XKHH25KN","canonical_record":{"source":{"id":"2006.11984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T03:13:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5254eec02bee1187cb0dec12d5cb1d049d2b7d90218bbfc11536ab97b500ba21","abstract_canon_sha256":"8152d512dc788fc9169b436289d2dfc366dacdc7614cb24bc07b095f27867ea7"},"schema_version":"1.0"},"canonical_sha256":"ba8e7d754d6a861c1061b66d6e0d4d5546ec8f2e350e34d826303135e8c0b845","source":{"kind":"arxiv","id":"2006.11984","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11984","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11984v1","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11984","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"pith_short_12","alias_value":"XKHH25KNNKDB","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"pith_short_16","alias_value":"XKHH25KNNKDBYEDB","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"pith_short_8","alias_value":"XKHH25KN","created_at":"2026-07-05T01:11:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XKHH25KNNKDBYEDBWZWW4DKNKV","target":"record","payload":{"canonical_record":{"source":{"id":"2006.11984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T03:13:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5254eec02bee1187cb0dec12d5cb1d049d2b7d90218bbfc11536ab97b500ba21","abstract_canon_sha256":"8152d512dc788fc9169b436289d2dfc366dacdc7614cb24bc07b095f27867ea7"},"schema_version":"1.0"},"canonical_sha256":"ba8e7d754d6a861c1061b66d6e0d4d5546ec8f2e350e34d826303135e8c0b845","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:55.529418Z","signature_b64":"8Oh+mg2SeDmE4rCVdWYcgDnQZwEU6mEQd1a2KjRHO1g5Ui7aBvRQ/mU0C/nP5vP/NL2GYVcw6AvQkOelwUCJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba8e7d754d6a861c1061b66d6e0d4d5546ec8f2e350e34d826303135e8c0b845","last_reissued_at":"2026-07-05T01:11:55.529008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:55.529008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.11984","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":"2026-07-05T01:11:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DAMKnshPOpUufWYhj36ezn4Tt1eUjSSYWm2/Yi3Lp+Y1MvIkDxEveQ8JN7zkvEtIzDF3nLBObnZGpaBcY/LUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:32:51.603455Z"},"content_sha256":"749c4ec4c562f7c33a2b3f9903aa686314bd779461ed6ed28d048d576bd57d0a","schema_version":"1.0","event_id":"sha256:749c4ec4c562f7c33a2b3f9903aa686314bd779461ed6ed28d048d576bd57d0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XKHH25KNNKDBYEDBWZWW4DKNKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Combinatorial Optimization with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Josu Ceberio, Martin Tak\\'a\\v{c}, Ruben Solozabal","submitted_at":"2020-06-22T03:13:07Z","abstract_excerpt":"This paper presents a framework to tackle constrained combinatorial optimization problems using deep Reinforcement Learning (RL). To this end, we extend the Neural Combinatorial Optimization (NCO) theory in order to deal with constraints in its formulation.\n  Notably, we propose defining constrained combinatorial problems as fully observable Constrained Markov Decision Processes (CMDP). In that context, the solution is iteratively constructed based on interactions with the environment. The model, in addition to the reward signal, relies on penalty signals generated from constraint dissatisfact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11984","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/2006.11984/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":"2026-07-05T01:11:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qsAa07g96TrdpPNa2hC8pr5sWtEJpPu1ic1KUlA3PFZcioD59kWponBInQ1JG/bEX06AB+yajuYZUwi7fTIcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:32:51.603975Z"},"content_sha256":"7fc923a380988d0bdef77049bfda2df8251509a8bae3161c8d61426aae6ffe0e","schema_version":"1.0","event_id":"sha256:7fc923a380988d0bdef77049bfda2df8251509a8bae3161c8d61426aae6ffe0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKHH25KNNKDBYEDBWZWW4DKNKV/bundle.json","state_url":"https://pith.science/pith/XKHH25KNNKDBYEDBWZWW4DKNKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKHH25KNNKDBYEDBWZWW4DKNKV/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":"2026-08-21T00:32:51Z","links":{"resolver":"https://pith.science/pith/XKHH25KNNKDBYEDBWZWW4DKNKV","bundle":"https://pith.science/pith/XKHH25KNNKDBYEDBWZWW4DKNKV/bundle.json","state":"https://pith.science/pith/XKHH25KNNKDBYEDBWZWW4DKNKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKHH25KNNKDBYEDBWZWW4DKNKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XKHH25KNNKDBYEDBWZWW4DKNKV","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":"8152d512dc788fc9169b436289d2dfc366dacdc7614cb24bc07b095f27867ea7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T03:13:07Z","title_canon_sha256":"5254eec02bee1187cb0dec12d5cb1d049d2b7d90218bbfc11536ab97b500ba21"},"schema_version":"1.0","source":{"id":"2006.11984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11984","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11984v1","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11984","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"pith_short_12","alias_value":"XKHH25KNNKDB","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"pith_short_16","alias_value":"XKHH25KNNKDBYEDB","created_at":"2026-07-05T01:11:55Z"},{"alias_kind":"pith_short_8","alias_value":"XKHH25KN","created_at":"2026-07-05T01:11:55Z"}],"graph_snapshots":[{"event_id":"sha256:7fc923a380988d0bdef77049bfda2df8251509a8bae3161c8d61426aae6ffe0e","target":"graph","created_at":"2026-07-05T01:11:55Z","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/2006.11984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a framework to tackle constrained combinatorial optimization problems using deep Reinforcement Learning (RL). To this end, we extend the Neural Combinatorial Optimization (NCO) theory in order to deal with constraints in its formulation.\n  Notably, we propose defining constrained combinatorial problems as fully observable Constrained Markov Decision Processes (CMDP). In that context, the solution is iteratively constructed based on interactions with the environment. The model, in addition to the reward signal, relies on penalty signals generated from constraint dissatisfact","authors_text":"Josu Ceberio, Martin Tak\\'a\\v{c}, Ruben Solozabal","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T03:13:07Z","title":"Constrained Combinatorial Optimization with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11984","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":"sha256:749c4ec4c562f7c33a2b3f9903aa686314bd779461ed6ed28d048d576bd57d0a","target":"record","created_at":"2026-07-05T01:11:55Z","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":"8152d512dc788fc9169b436289d2dfc366dacdc7614cb24bc07b095f27867ea7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T03:13:07Z","title_canon_sha256":"5254eec02bee1187cb0dec12d5cb1d049d2b7d90218bbfc11536ab97b500ba21"},"schema_version":"1.0","source":{"id":"2006.11984","kind":"arxiv","version":1}},"canonical_sha256":"ba8e7d754d6a861c1061b66d6e0d4d5546ec8f2e350e34d826303135e8c0b845","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba8e7d754d6a861c1061b66d6e0d4d5546ec8f2e350e34d826303135e8c0b845","first_computed_at":"2026-07-05T01:11:55.529008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:55.529008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Oh+mg2SeDmE4rCVdWYcgDnQZwEU6mEQd1a2KjRHO1g5Ui7aBvRQ/mU0C/nP5vP/NL2GYVcw6AvQkOelwUCJBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:55.529418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.11984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:749c4ec4c562f7c33a2b3f9903aa686314bd779461ed6ed28d048d576bd57d0a","sha256:7fc923a380988d0bdef77049bfda2df8251509a8bae3161c8d61426aae6ffe0e"],"state_sha256":"65e2f8c1a360f903813235d56dcd9676d816374e66a453bdec158fdbb3c07a05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVYwFa3/0JzNpc8WmgVLeEVFQtU2UyR9f3+AiC5ZRK+5bPea2PeYsm/liBWzD12/hB/5Io6sy3B8OfaYJx0mAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T00:32:51.610434Z","bundle_sha256":"57689eaf3c8935635cee5c1c321d7684e30d71534b4d17813d2e2f157fe8db17"}}