{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RI4PRR3YIBDF5P6XH2WVWDXLOD","short_pith_number":"pith:RI4PRR3Y","schema_version":"1.0","canonical_sha256":"8a38f8c77840465ebfd73ead5b0eeb70c6c92d72637dcd3b7be5954af6e3ec61","source":{"kind":"arxiv","id":"1909.04063","version":2},"attestation_state":"computed","paper":{"title":"Exploratory Combinatorial Optimization with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"A. I. Lvovsky, Jakob N. Foerster, Thomas D. Barrett, William R. Clements","submitted_at":"2019-09-09T18:00:24Z","abstract_excerpt":"Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable, reinforcement learning (RL) has shown promise as a framework with which efficient heuristic methods to tackle these problems can be learned. Previous works construct the solution subset incrementally, adding one element at a time, however, the irreversible nature of this approach prevents the agent from revising its earlier decisions, which may be necessary give"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1909.04063","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T18:00:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2cd1727abb92d27c2cfcecade040b11239d03b4b9aa1753a3a376a6e45fa8d28","abstract_canon_sha256":"0b8493d6c2d3671cab39796bbeec234a0a5ddb1cb2d995240ffe08181a34e079"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:27.686405Z","signature_b64":"T4c+q6YYKEQTPhLrSuFj7jNR+81gHuj5hBUXVr1wG/I+URQNTd/wxbRw5UK+T7++Ck7VATHH2l9DVjfRMWLwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a38f8c77840465ebfd73ead5b0eeb70c6c92d72637dcd3b7be5954af6e3ec61","last_reissued_at":"2026-07-05T02:24:27.685961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:27.685961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploratory Combinatorial Optimization with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"A. I. Lvovsky, Jakob N. Foerster, Thomas D. Barrett, William R. Clements","submitted_at":"2019-09-09T18:00:24Z","abstract_excerpt":"Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable, reinforcement learning (RL) has shown promise as a framework with which efficient heuristic methods to tackle these problems can be learned. Previous works construct the solution subset incrementally, adding one element at a time, however, the irreversible nature of this approach prevents the agent from revising its earlier decisions, which may be necessary give"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04063","kind":"arxiv","version":2},"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/1909.04063/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1909.04063","created_at":"2026-07-05T02:24:27.686021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.04063v2","created_at":"2026-07-05T02:24:27.686021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04063","created_at":"2026-07-05T02:24:27.686021+00:00"},{"alias_kind":"pith_short_12","alias_value":"RI4PRR3YIBDF","created_at":"2026-07-05T02:24:27.686021+00:00"},{"alias_kind":"pith_short_16","alias_value":"RI4PRR3YIBDF5P6X","created_at":"2026-07-05T02:24:27.686021+00:00"},{"alias_kind":"pith_short_8","alias_value":"RI4PRR3Y","created_at":"2026-07-05T02:24:27.686021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10520","citing_title":"Nonlocal Monte Carlo via Reinforcement Learning","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD","json":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD.json","graph_json":"https://pith.science/api/pith-number/RI4PRR3YIBDF5P6XH2WVWDXLOD/graph.json","events_json":"https://pith.science/api/pith-number/RI4PRR3YIBDF5P6XH2WVWDXLOD/events.json","paper":"https://pith.science/paper/RI4PRR3Y"},"agent_actions":{"view_html":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD","download_json":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD.json","view_paper":"https://pith.science/paper/RI4PRR3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.04063&json=true","fetch_graph":"https://pith.science/api/pith-number/RI4PRR3YIBDF5P6XH2WVWDXLOD/graph.json","fetch_events":"https://pith.science/api/pith-number/RI4PRR3YIBDF5P6XH2WVWDXLOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD/action/storage_attestation","attest_author":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD/action/author_attestation","sign_citation":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD/action/citation_signature","submit_replication":"https://pith.science/pith/RI4PRR3YIBDF5P6XH2WVWDXLOD/action/replication_record"}},"created_at":"2026-07-05T02:24:27.686021+00:00","updated_at":"2026-07-05T02:24:27.686021+00:00"}