{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I6HXFJMWTROP7Y2NNJ73ZYTJYO","short_pith_number":"pith:I6HXFJMW","schema_version":"1.0","canonical_sha256":"478f72a5969c5cffe34d6a7fbce269c39843dbcf22d8e762ab2c8d5d6b393b35","source":{"kind":"arxiv","id":"1906.01227","version":2},"attestation_state":"computed","paper":{"title":"An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaitanya K. Joshi, Thomas Laurent, Xavier Bresson","submitted_at":"2019-06-04T06:51:45Z","abstract_excerpt":"This paper introduces a new learning-based approach for approximately solving the Travelling Salesman Problem on 2D Euclidean graphs. We use deep Graph Convolutional Networks to build efficient TSP graph representations and output tours in a non-autoregressive manner via highly parallelized beam search. Our approach outperforms all recently proposed autoregressive deep learning techniques in terms of solution quality, inference speed and sample efficiency for problem instances of fixed graph sizes. In particular, we reduce the average optimality gap from 0.52% to 0.01% for 50 nodes, and from 2"},"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":"1906.01227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T06:51:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"73a460651fcb664b1e5a3e82faa47b32aefe6cd3cb1de383813beff8d657021b","abstract_canon_sha256":"3e9359737f169a8d2afb8815954eb770b28c26f51ed482a772d8bb1c7c66e285"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:34.374654Z","signature_b64":"G3H8Gpltv4uc88gh2iP8i42ONhpgTuPINERULMYPxr+z9Mxy+DPfEcek6xnr66XRYDw/p35BvOxmghBEI24uAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"478f72a5969c5cffe34d6a7fbce269c39843dbcf22d8e762ab2c8d5d6b393b35","last_reissued_at":"2026-07-05T00:11:34.374135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:34.374135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaitanya K. Joshi, Thomas Laurent, Xavier Bresson","submitted_at":"2019-06-04T06:51:45Z","abstract_excerpt":"This paper introduces a new learning-based approach for approximately solving the Travelling Salesman Problem on 2D Euclidean graphs. We use deep Graph Convolutional Networks to build efficient TSP graph representations and output tours in a non-autoregressive manner via highly parallelized beam search. Our approach outperforms all recently proposed autoregressive deep learning techniques in terms of solution quality, inference speed and sample efficiency for problem instances of fixed graph sizes. In particular, we reduce the average optimality gap from 0.52% to 0.01% for 50 nodes, and from 2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01227","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/1906.01227/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":"1906.01227","created_at":"2026-07-05T00:11:34.374200+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01227v2","created_at":"2026-07-05T00:11:34.374200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01227","created_at":"2026-07-05T00:11:34.374200+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6HXFJMWTROP","created_at":"2026-07-05T00:11:34.374200+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6HXFJMWTROP7Y2N","created_at":"2026-07-05T00:11:34.374200+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6HXFJMW","created_at":"2026-07-05T00:11:34.374200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26873","citing_title":"Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman Hierarchy","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22776","citing_title":"GeoRouteNet: A Geometry-Aware Non-Autoregressive Neural Solver for the Euclidean Traveling Salesman Problem","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19185","citing_title":"AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10431","citing_title":"Vision-Assisted Foundation Model for Solving Multi-Task Vehicle Routing Problems","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01185","citing_title":"Neural Certificate Pricing for Combinatorial Optimization Problems","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23395","citing_title":"Convex Compositional Reasoning Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24484","citing_title":"SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29725","citing_title":"Optimizing Nursing Care Taxi Dispatch Leveraging Integer Linear Programming Solvers and Machine Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26776","citing_title":"Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02294","citing_title":"Regularized Large Neighborhood Search","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23395","citing_title":"Convex Compositional Reasoning Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16409","citing_title":"Network Interdiction Goes Neural","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2405.15314","citing_title":"Output-Constrained Decision Trees","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2406.03099","citing_title":"Supplementary Materials to Graph Convolutional Branch and Bound","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17539","citing_title":"Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19119","citing_title":"GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20169","citing_title":"Empowering Targeted Neighborhood Search via Hyper Tour for Large-Scale TSP","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20236","citing_title":"Machine Learning-based Two-Stage Graph Sparsification for the Travelling Salesman Problem","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO","json":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO.json","graph_json":"https://pith.science/api/pith-number/I6HXFJMWTROP7Y2NNJ73ZYTJYO/graph.json","events_json":"https://pith.science/api/pith-number/I6HXFJMWTROP7Y2NNJ73ZYTJYO/events.json","paper":"https://pith.science/paper/I6HXFJMW"},"agent_actions":{"view_html":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO","download_json":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO.json","view_paper":"https://pith.science/paper/I6HXFJMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01227&json=true","fetch_graph":"https://pith.science/api/pith-number/I6HXFJMWTROP7Y2NNJ73ZYTJYO/graph.json","fetch_events":"https://pith.science/api/pith-number/I6HXFJMWTROP7Y2NNJ73ZYTJYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO/action/storage_attestation","attest_author":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO/action/author_attestation","sign_citation":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO/action/citation_signature","submit_replication":"https://pith.science/pith/I6HXFJMWTROP7Y2NNJ73ZYTJYO/action/replication_record"}},"created_at":"2026-07-05T00:11:34.374200+00:00","updated_at":"2026-07-05T00:11:34.374200+00:00"}