{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RI4PRR3YIBDF5P6XH2WVWDXLOD","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":"0b8493d6c2d3671cab39796bbeec234a0a5ddb1cb2d995240ffe08181a34e079","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T18:00:24Z","title_canon_sha256":"2cd1727abb92d27c2cfcecade040b11239d03b4b9aa1753a3a376a6e45fa8d28"},"schema_version":"1.0","source":{"id":"1909.04063","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.04063","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"arxiv_version","alias_value":"1909.04063v2","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04063","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_12","alias_value":"RI4PRR3YIBDF","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_16","alias_value":"RI4PRR3YIBDF5P6X","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_8","alias_value":"RI4PRR3Y","created_at":"2026-07-05T02:24:27Z"}],"graph_snapshots":[{"event_id":"sha256:2526699ca09e5a6f6600713373e5e01143c25a151be59d8a4ea59611f0d0e9cf","target":"graph","created_at":"2026-07-05T02:24:27Z","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/1909.04063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"A. I. Lvovsky, Jakob N. Foerster, Thomas D. Barrett, William R. Clements","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T18:00:24Z","title":"Exploratory Combinatorial Optimization with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04063","kind":"arxiv","version":2},"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:cb015736ccdfa0f66e27e402192ed76cdc50c50020928d9ea26a61cf7f4f1383","target":"record","created_at":"2026-07-05T02:24:27Z","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":"0b8493d6c2d3671cab39796bbeec234a0a5ddb1cb2d995240ffe08181a34e079","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T18:00:24Z","title_canon_sha256":"2cd1727abb92d27c2cfcecade040b11239d03b4b9aa1753a3a376a6e45fa8d28"},"schema_version":"1.0","source":{"id":"1909.04063","kind":"arxiv","version":2}},"canonical_sha256":"8a38f8c77840465ebfd73ead5b0eeb70c6c92d72637dcd3b7be5954af6e3ec61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a38f8c77840465ebfd73ead5b0eeb70c6c92d72637dcd3b7be5954af6e3ec61","first_computed_at":"2026-07-05T02:24:27.685961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:27.685961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T4c+q6YYKEQTPhLrSuFj7jNR+81gHuj5hBUXVr1wG/I+URQNTd/wxbRw5UK+T7++Ck7VATHH2l9DVjfRMWLwBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:27.686405Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.04063","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb015736ccdfa0f66e27e402192ed76cdc50c50020928d9ea26a61cf7f4f1383","sha256:2526699ca09e5a6f6600713373e5e01143c25a151be59d8a4ea59611f0d0e9cf"],"state_sha256":"9c3b2ab67e7ae86bde809308146f007cfcb8bf4f4f5b20f5c6b4976a7963b34e"}