{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NGZKRJTVWOISWFQW474HCM6YAR","short_pith_number":"pith:NGZKRJTV","schema_version":"1.0","canonical_sha256":"69b2a8a675b3912b1616e7f87133d8045d119521bb35d39fd5894afe8209e367","source":{"kind":"arxiv","id":"2605.30920","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shengyu Feng, Tarun Suresh, Yiming Yang","submitted_at":"2026-05-29T07:04:42Z","abstract_excerpt":"Diffusion-based neural solvers have shown strong promise for combinatorial optimization (CO), but existing methods typically rely on supervised training with large collections of near-optimal solutions. In this work, we extend adjoint-based trajectory optimization methods to discrete combinatorial domains. We formulate diffusion-based CO as a stochastic control problem over Continuous-Time Markov Chains and introduce discrete adjoint dynamics for propagating optimization signals through discrete generative trajectories. Building on this formulation, we propose Combinatorial Adjoint Matching (C"},"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":"2605.30920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T07:04:42Z","cross_cats_sorted":[],"title_canon_sha256":"75c07a730f756b88074172cba4929627c69baae61ddb3608fa69391531c8a5a5","abstract_canon_sha256":"583f9cb7a9aa0dca5a8f45a81e8548edf1bfcce02dd3055b438c30d46747e3f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:25.961304Z","signature_b64":"KbKz+UpkEbuE7P70O/oarawqCpkFZTiVPuzfWeI2Wyl6dYJE4IcYc6Efv3MAoM0j2vCE34vEBHugr5SXficRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69b2a8a675b3912b1616e7f87133d8045d119521bb35d39fd5894afe8209e367","last_reissued_at":"2026-06-01T01:03:25.960276Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:25.960276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shengyu Feng, Tarun Suresh, Yiming Yang","submitted_at":"2026-05-29T07:04:42Z","abstract_excerpt":"Diffusion-based neural solvers have shown strong promise for combinatorial optimization (CO), but existing methods typically rely on supervised training with large collections of near-optimal solutions. In this work, we extend adjoint-based trajectory optimization methods to discrete combinatorial domains. We formulate diffusion-based CO as a stochastic control problem over Continuous-Time Markov Chains and introduce discrete adjoint dynamics for propagating optimization signals through discrete generative trajectories. Building on this formulation, we propose Combinatorial Adjoint Matching (C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30920","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/2605.30920/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":"2605.30920","created_at":"2026-06-01T01:03:25.960573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30920v1","created_at":"2026-06-01T01:03:25.960573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30920","created_at":"2026-06-01T01:03:25.960573+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGZKRJTVWOIS","created_at":"2026-06-01T01:03:25.960573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGZKRJTVWOISWFQW","created_at":"2026-06-01T01:03:25.960573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGZKRJTV","created_at":"2026-06-01T01:03:25.960573+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/NGZKRJTVWOISWFQW474HCM6YAR","json":"https://pith.science/pith/NGZKRJTVWOISWFQW474HCM6YAR.json","graph_json":"https://pith.science/api/pith-number/NGZKRJTVWOISWFQW474HCM6YAR/graph.json","events_json":"https://pith.science/api/pith-number/NGZKRJTVWOISWFQW474HCM6YAR/events.json","paper":"https://pith.science/paper/NGZKRJTV"},"agent_actions":{"view_html":"https://pith.science/pith/NGZKRJTVWOISWFQW474HCM6YAR","download_json":"https://pith.science/pith/NGZKRJTVWOISWFQW474HCM6YAR.json","view_paper":"https://pith.science/paper/NGZKRJTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30920&json=true","fetch_graph":"https://pith.science/api/pith-number/NGZKRJTVWOISWFQW474HCM6YAR/graph.json","fetch_events":"https://pith.science/api/pith-number/NGZKRJTVWOISWFQW474HCM6YAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGZKRJTVWOISWFQW474HCM6YAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGZKRJTVWOISWFQW474HCM6YAR/action/storage_attestation","attest_author":"https://pith.science/pith/NGZKRJTVWOISWFQW474HCM6YAR/action/author_attestation","sign_citation":"https://pith.science/pith/NGZKRJTVWOISWFQW474HCM6YAR/action/citation_signature","submit_replication":"https://pith.science/pith/NGZKRJTVWOISWFQW474HCM6YAR/action/replication_record"}},"created_at":"2026-06-01T01:03:25.960573+00:00","updated_at":"2026-06-01T01:03:25.960573+00:00"}