{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RYQGUFSJTFZLYQRCLEYH23NG5E","short_pith_number":"pith:RYQGUFSJ","schema_version":"1.0","canonical_sha256":"8e206a16499972bc422259307d6da6e91c70635d91465c9845059dba62180315","source":{"kind":"arxiv","id":"2106.03594","version":3},"attestation_state":"computed","paper":{"title":"Learning Combinatorial Node Labeling Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lukas Gianinazzi, Maciej Besta, Maximilian Fries, Nikoli Dryden, Tal Ben-Nun, Torsten Hoefler","submitted_at":"2021-06-07T13:21:09Z","abstract_excerpt":"We present a novel neural architecture to solve graph optimization problems where the solution consists of arbitrary node labels, allowing us to solve hard problems like graph coloring. We train our model using reinforcement learning, specifically policy gradients, which gives us both a greedy and a probabilistic policy. Our architecture builds on a graph attention network and uses several inductive biases to improve solution quality. Our learned deterministic heuristics for graph coloring give better solutions than classical degree-based greedy heuristics and only take seconds to apply to gra"},"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":"2106.03594","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T13:21:09Z","cross_cats_sorted":[],"title_canon_sha256":"f4e1e8052e997a47ca0908ed0eb4e24c36c34dab2b6227822c59c471fbb40880","abstract_canon_sha256":"148999a0c4619ea6cebd10a3a8bbdde50e039694ab1a53bb60f592f84885522b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:47.203801Z","signature_b64":"klckJljk+qKSDhR8sAqoOgHiR7uXzCNkrFLqOYD+YvFNS1xBV96Cw9hF6Ldgb+wASnOfvPX/1yMQDsxjVNV8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e206a16499972bc422259307d6da6e91c70635d91465c9845059dba62180315","last_reissued_at":"2026-07-05T04:21:47.203281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:47.203281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Combinatorial Node Labeling Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lukas Gianinazzi, Maciej Besta, Maximilian Fries, Nikoli Dryden, Tal Ben-Nun, Torsten Hoefler","submitted_at":"2021-06-07T13:21:09Z","abstract_excerpt":"We present a novel neural architecture to solve graph optimization problems where the solution consists of arbitrary node labels, allowing us to solve hard problems like graph coloring. We train our model using reinforcement learning, specifically policy gradients, which gives us both a greedy and a probabilistic policy. Our architecture builds on a graph attention network and uses several inductive biases to improve solution quality. Our learned deterministic heuristics for graph coloring give better solutions than classical degree-based greedy heuristics and only take seconds to apply to gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03594","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.03594/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":"2106.03594","created_at":"2026-07-05T04:21:47.203348+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03594v3","created_at":"2026-07-05T04:21:47.203348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03594","created_at":"2026-07-05T04:21:47.203348+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYQGUFSJTFZL","created_at":"2026-07-05T04:21:47.203348+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYQGUFSJTFZLYQRC","created_at":"2026-07-05T04:21:47.203348+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYQGUFSJ","created_at":"2026-07-05T04:21:47.203348+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06682","citing_title":"Learning Robust Heterogeneous Graph Representations via Contrastive-Reconstruction under Sparse Semantics","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E","json":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E.json","graph_json":"https://pith.science/api/pith-number/RYQGUFSJTFZLYQRCLEYH23NG5E/graph.json","events_json":"https://pith.science/api/pith-number/RYQGUFSJTFZLYQRCLEYH23NG5E/events.json","paper":"https://pith.science/paper/RYQGUFSJ"},"agent_actions":{"view_html":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E","download_json":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E.json","view_paper":"https://pith.science/paper/RYQGUFSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03594&json=true","fetch_graph":"https://pith.science/api/pith-number/RYQGUFSJTFZLYQRCLEYH23NG5E/graph.json","fetch_events":"https://pith.science/api/pith-number/RYQGUFSJTFZLYQRCLEYH23NG5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E/action/storage_attestation","attest_author":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E/action/author_attestation","sign_citation":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E/action/citation_signature","submit_replication":"https://pith.science/pith/RYQGUFSJTFZLYQRCLEYH23NG5E/action/replication_record"}},"created_at":"2026-07-05T04:21:47.203348+00:00","updated_at":"2026-07-05T04:21:47.203348+00:00"}