{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BZS6D6UXLJS4QKUDS4KGOM6QNJ","short_pith_number":"pith:BZS6D6UX","schema_version":"1.0","canonical_sha256":"0e65e1fa975a65c82a8397146733d06a6b39849655826a96d4b5ee375b01bb44","source":{"kind":"arxiv","id":"2110.02843","version":1},"attestation_state":"computed","paper":{"title":"Improving Generalization of Deep Reinforcement Learning-based TSP Solvers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Paul Weng, Shaochen Han, Wenbin Ouyang, Yisen Wang, Zhejian Jin","submitted_at":"2021-10-06T15:16:19Z","abstract_excerpt":"Recent work applying deep reinforcement learning (DRL) to solve traveling salesman problems (TSP) has shown that DRL-based solvers can be fast and competitive with TSP heuristics for small instances, but do not generalize well to larger instances. In this work, we propose a novel approach named MAGIC that includes a deep learning architecture and a DRL training method. Our architecture, which integrates a multilayer perceptron, a graph neural network, and an attention model, defines a stochastic policy that sequentially generates a TSP solution. Our training method includes several innovations"},"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":"2110.02843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T15:16:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ab380d113428888c88324ecb98d44748b41bd8ffa27782e7b0e203083e32904b","abstract_canon_sha256":"8d7ce892ec3bc2b253516af5b4b4075a7f598056fcd5149fa14110750ae5db15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:30.522556Z","signature_b64":"ywr8CJv2gD8CTsSykFGGqqoWrL2ZInMNuaHDxnQXuxO62KgJmIgAVc4z17sVzaEJ+P+oO6DKPEtwP7USaF4AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e65e1fa975a65c82a8397146733d06a6b39849655826a96d4b5ee375b01bb44","last_reissued_at":"2026-07-05T03:20:30.522158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:30.522158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Generalization of Deep Reinforcement Learning-based TSP Solvers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Paul Weng, Shaochen Han, Wenbin Ouyang, Yisen Wang, Zhejian Jin","submitted_at":"2021-10-06T15:16:19Z","abstract_excerpt":"Recent work applying deep reinforcement learning (DRL) to solve traveling salesman problems (TSP) has shown that DRL-based solvers can be fast and competitive with TSP heuristics for small instances, but do not generalize well to larger instances. In this work, we propose a novel approach named MAGIC that includes a deep learning architecture and a DRL training method. Our architecture, which integrates a multilayer perceptron, a graph neural network, and an attention model, defines a stochastic policy that sequentially generates a TSP solution. Our training method includes several innovations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02843","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/2110.02843/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":"2110.02843","created_at":"2026-07-05T03:20:30.522221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02843v1","created_at":"2026-07-05T03:20:30.522221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02843","created_at":"2026-07-05T03:20:30.522221+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZS6D6UXLJS4","created_at":"2026-07-05T03:20:30.522221+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZS6D6UXLJS4QKUD","created_at":"2026-07-05T03:20:30.522221+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZS6D6UX","created_at":"2026-07-05T03:20:30.522221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ","json":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ.json","graph_json":"https://pith.science/api/pith-number/BZS6D6UXLJS4QKUDS4KGOM6QNJ/graph.json","events_json":"https://pith.science/api/pith-number/BZS6D6UXLJS4QKUDS4KGOM6QNJ/events.json","paper":"https://pith.science/paper/BZS6D6UX"},"agent_actions":{"view_html":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ","download_json":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ.json","view_paper":"https://pith.science/paper/BZS6D6UX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02843&json=true","fetch_graph":"https://pith.science/api/pith-number/BZS6D6UXLJS4QKUDS4KGOM6QNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BZS6D6UXLJS4QKUDS4KGOM6QNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ/action/storage_attestation","attest_author":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ/action/author_attestation","sign_citation":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ/action/citation_signature","submit_replication":"https://pith.science/pith/BZS6D6UXLJS4QKUDS4KGOM6QNJ/action/replication_record"}},"created_at":"2026-07-05T03:20:30.522221+00:00","updated_at":"2026-07-05T03:20:30.522221+00:00"}