{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:POTT4DEVNLEXZFAK73XTGSLHMX","short_pith_number":"pith:POTT4DEV","schema_version":"1.0","canonical_sha256":"7ba73e0c956ac97c940afeef33496765df696b3ca7469455d0dfb9cd306e9169","source":{"kind":"arxiv","id":"2205.14105","version":1},"attestation_state":"computed","paper":{"title":"Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandre Laterre, Christopher W.F. Parsonson, Thomas D. Barrett","submitted_at":"2022-05-27T17:13:10Z","abstract_excerpt":"From logistics to the natural sciences, combinatorial optimisation on graphs underpins numerous real-world applications. Reinforcement learning (RL) has shown particular promise in this setting as it can adapt to specific problem structures and does not require pre-solved instances for these, often NP-hard, problems. However, state-of-the-art (SOTA) approaches typically suffer from severe scalability issues, primarily due to their reliance on expensive graph neural networks (GNNs) at each decision step. We introduce ECORD; a novel RL algorithm that alleviates this expense by restricting the GN"},"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":"2205.14105","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T17:13:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9e923211cc9af7573094c6b2ec5f241309ecf77c312aa3dff437812e58bc5e3","abstract_canon_sha256":"7a0cc481a2357af4ea855bad08e3212464187469ba18af7aada67a1c240feeae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:01.547073Z","signature_b64":"EjcH6Tn0hU3MYFp2aTuQS4XAO2cLLlT1HtnGX8t1Sgk5NqBM8VFkyfcdfaFx8+n9/IJ5TMa5q0HHA9LEWzdEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ba73e0c956ac97c940afeef33496765df696b3ca7469455d0dfb9cd306e9169","last_reissued_at":"2026-07-05T04:27:01.546585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:01.546585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandre Laterre, Christopher W.F. Parsonson, Thomas D. Barrett","submitted_at":"2022-05-27T17:13:10Z","abstract_excerpt":"From logistics to the natural sciences, combinatorial optimisation on graphs underpins numerous real-world applications. Reinforcement learning (RL) has shown particular promise in this setting as it can adapt to specific problem structures and does not require pre-solved instances for these, often NP-hard, problems. However, state-of-the-art (SOTA) approaches typically suffer from severe scalability issues, primarily due to their reliance on expensive graph neural networks (GNNs) at each decision step. We introduce ECORD; a novel RL algorithm that alleviates this expense by restricting the GN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14105","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/2205.14105/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":"2205.14105","created_at":"2026-07-05T04:27:01.546638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14105v1","created_at":"2026-07-05T04:27:01.546638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14105","created_at":"2026-07-05T04:27:01.546638+00:00"},{"alias_kind":"pith_short_12","alias_value":"POTT4DEVNLEX","created_at":"2026-07-05T04:27:01.546638+00:00"},{"alias_kind":"pith_short_16","alias_value":"POTT4DEVNLEXZFAK","created_at":"2026-07-05T04:27:01.546638+00:00"},{"alias_kind":"pith_short_8","alias_value":"POTT4DEV","created_at":"2026-07-05T04:27:01.546638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25129","citing_title":"Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX","json":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX.json","graph_json":"https://pith.science/api/pith-number/POTT4DEVNLEXZFAK73XTGSLHMX/graph.json","events_json":"https://pith.science/api/pith-number/POTT4DEVNLEXZFAK73XTGSLHMX/events.json","paper":"https://pith.science/paper/POTT4DEV"},"agent_actions":{"view_html":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX","download_json":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX.json","view_paper":"https://pith.science/paper/POTT4DEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14105&json=true","fetch_graph":"https://pith.science/api/pith-number/POTT4DEVNLEXZFAK73XTGSLHMX/graph.json","fetch_events":"https://pith.science/api/pith-number/POTT4DEVNLEXZFAK73XTGSLHMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX/action/storage_attestation","attest_author":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX/action/author_attestation","sign_citation":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX/action/citation_signature","submit_replication":"https://pith.science/pith/POTT4DEVNLEXZFAK73XTGSLHMX/action/replication_record"}},"created_at":"2026-07-05T04:27:01.546638+00:00","updated_at":"2026-07-05T04:27:01.546638+00:00"}