{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EEE5NNJM4JNQ2PVYEIRCPCRLJE","short_pith_number":"pith:EEE5NNJM","schema_version":"1.0","canonical_sha256":"2109d6b52ce25b0d3eb82222278a2b493ff4a648d0f9a1e10c12118861c23a5f","source":{"kind":"arxiv","id":"2503.04047","version":1},"attestation_state":"computed","paper":{"title":"Reheated Gradient-based Discrete Sampling for Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Muheng Li, Ruqi Zhang","submitted_at":"2025-03-06T03:01:25Z","abstract_excerpt":"Recently, gradient-based discrete sampling has emerged as a highly efficient, general-purpose solver for various combinatorial optimization (CO) problems, achieving performance comparable to or surpassing the popular data-driven approaches. However, we identify a critical issue in these methods, which we term ''wandering in contours''. This behavior refers to sampling new different solutions that share very similar objective values for a long time, leading to computational inefficiency and suboptimal exploration of potential solutions. In this paper, we introduce a novel reheating mechanism in"},"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":"2503.04047","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-03-06T03:01:25Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"775150352e585dcf92e149aaedfbb967e4f4aa3c518cbf0e36e232a820887c9f","abstract_canon_sha256":"25a3e52de2394c5c192d40692d8f213de3a3ce3ebbe6687f145c996f794d123a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:27.390267Z","signature_b64":"eFqjfWZjTM4iAoauSfLEeplcW1R9f5yQbuq53u4z2EFrseUusgRKx1m5DffSeRZbqbtx3usdhX9Zp6ampgPsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2109d6b52ce25b0d3eb82222278a2b493ff4a648d0f9a1e10c12118861c23a5f","last_reissued_at":"2026-07-05T10:25:27.389480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:27.389480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reheated Gradient-based Discrete Sampling for Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Muheng Li, Ruqi Zhang","submitted_at":"2025-03-06T03:01:25Z","abstract_excerpt":"Recently, gradient-based discrete sampling has emerged as a highly efficient, general-purpose solver for various combinatorial optimization (CO) problems, achieving performance comparable to or surpassing the popular data-driven approaches. However, we identify a critical issue in these methods, which we term ''wandering in contours''. This behavior refers to sampling new different solutions that share very similar objective values for a long time, leading to computational inefficiency and suboptimal exploration of potential solutions. In this paper, we introduce a novel reheating mechanism in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04047","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/2503.04047/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":"2503.04047","created_at":"2026-07-05T10:25:27.389583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04047v1","created_at":"2026-07-05T10:25:27.389583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04047","created_at":"2026-07-05T10:25:27.389583+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEE5NNJM4JNQ","created_at":"2026-07-05T10:25:27.389583+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEE5NNJM4JNQ2PVY","created_at":"2026-07-05T10:25:27.389583+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEE5NNJM","created_at":"2026-07-05T10:25:27.389583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29366","citing_title":"Solving Integer Linear Programming with Parallel Tempering","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE","json":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE.json","graph_json":"https://pith.science/api/pith-number/EEE5NNJM4JNQ2PVYEIRCPCRLJE/graph.json","events_json":"https://pith.science/api/pith-number/EEE5NNJM4JNQ2PVYEIRCPCRLJE/events.json","paper":"https://pith.science/paper/EEE5NNJM"},"agent_actions":{"view_html":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE","download_json":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE.json","view_paper":"https://pith.science/paper/EEE5NNJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04047&json=true","fetch_graph":"https://pith.science/api/pith-number/EEE5NNJM4JNQ2PVYEIRCPCRLJE/graph.json","fetch_events":"https://pith.science/api/pith-number/EEE5NNJM4JNQ2PVYEIRCPCRLJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE/action/storage_attestation","attest_author":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE/action/author_attestation","sign_citation":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE/action/citation_signature","submit_replication":"https://pith.science/pith/EEE5NNJM4JNQ2PVYEIRCPCRLJE/action/replication_record"}},"created_at":"2026-07-05T10:25:27.389583+00:00","updated_at":"2026-07-05T10:25:27.389583+00:00"}