{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CVU66IUXFC5K26NWCGYMHSK7E2","short_pith_number":"pith:CVU66IUX","schema_version":"1.0","canonical_sha256":"1569ef229728baad79b611b0c3c95f26bb683efc6eacad0808137a8d71076238","source":{"kind":"arxiv","id":"2205.13209","version":2},"attestation_state":"computed","paper":{"title":"Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jinkyoo Park, Junyoung Park, Minsu Kim","submitted_at":"2022-05-26T07:55:43Z","abstract_excerpt":"Deep reinforcement learning (DRL)-based combinatorial optimization (CO) methods (i.e., DRL-NCO) have shown significant merit over the conventional CO solvers as DRL-NCO is capable of learning CO solvers less relying on problem-specific expert domain knowledge (heuristic method) and supervised labeled data (supervised learning method). This paper presents a novel training scheme, Sym-NCO, which is a regularizer-based training scheme that leverages universal symmetricities in various CO problems and solutions. Leveraging symmetricities such as rotational and reflectional invariance can greatly i"},"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":"2205.13209","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T07:55:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f3d10091d35eeddd851b94ca5b26112cdf3c83370c0389d7c7943d67123adeab","abstract_canon_sha256":"7febf8a1fab880bb3735bd16a0e51e3c43a5e0d29e82460c4bda93447b918978"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:55.082204Z","signature_b64":"aVyQnzsIJMursJsPczRgjdbBvs4Sg45jKfWJR6XCA7i6lvXhMYp1xG72OAxbrDp32wCedAY9Xd0zqlJsNf7YCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1569ef229728baad79b611b0c3c95f26bb683efc6eacad0808137a8d71076238","last_reissued_at":"2026-07-05T05:30:55.081867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:55.081867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jinkyoo Park, Junyoung Park, Minsu Kim","submitted_at":"2022-05-26T07:55:43Z","abstract_excerpt":"Deep reinforcement learning (DRL)-based combinatorial optimization (CO) methods (i.e., DRL-NCO) have shown significant merit over the conventional CO solvers as DRL-NCO is capable of learning CO solvers less relying on problem-specific expert domain knowledge (heuristic method) and supervised labeled data (supervised learning method). This paper presents a novel training scheme, Sym-NCO, which is a regularizer-based training scheme that leverages universal symmetricities in various CO problems and solutions. Leveraging symmetricities such as rotational and reflectional invariance can greatly i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13209","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/2205.13209/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":"2205.13209","created_at":"2026-07-05T05:30:55.081921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13209v2","created_at":"2026-07-05T05:30:55.081921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13209","created_at":"2026-07-05T05:30:55.081921+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVU66IUXFC5K","created_at":"2026-07-05T05:30:55.081921+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVU66IUXFC5K26NW","created_at":"2026-07-05T05:30:55.081921+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVU66IUX","created_at":"2026-07-05T05:30:55.081921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02941","citing_title":"Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2","json":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2.json","graph_json":"https://pith.science/api/pith-number/CVU66IUXFC5K26NWCGYMHSK7E2/graph.json","events_json":"https://pith.science/api/pith-number/CVU66IUXFC5K26NWCGYMHSK7E2/events.json","paper":"https://pith.science/paper/CVU66IUX"},"agent_actions":{"view_html":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2","download_json":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2.json","view_paper":"https://pith.science/paper/CVU66IUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13209&json=true","fetch_graph":"https://pith.science/api/pith-number/CVU66IUXFC5K26NWCGYMHSK7E2/graph.json","fetch_events":"https://pith.science/api/pith-number/CVU66IUXFC5K26NWCGYMHSK7E2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2/action/storage_attestation","attest_author":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2/action/author_attestation","sign_citation":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2/action/citation_signature","submit_replication":"https://pith.science/pith/CVU66IUXFC5K26NWCGYMHSK7E2/action/replication_record"}},"created_at":"2026-07-05T05:30:55.081921+00:00","updated_at":"2026-07-05T05:30:55.081921+00:00"}