{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PDBV5L7W2SVVSMR4R7XLE4PP6B","short_pith_number":"pith:PDBV5L7W","schema_version":"1.0","canonical_sha256":"78c35eaff6d4ab59323c8feeb271eff06b1f389efda0bbf17dbcbbc3af9273fd","source":{"kind":"arxiv","id":"2605.17362","version":1},"attestation_state":"computed","paper":{"title":"Learning Fill-in Reduction Ordering via Graph Policy Optimization for Sparse Matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huiyuan Li, Shuzi Niu, Tao Yuan, Wenjia Wu, Ziwei Li","submitted_at":"2026-05-17T10:07:23Z","abstract_excerpt":"Matrix reordering in large sparse solvers seeks a permutation that minimizes factorization fill-in to reduce memory and computation. Because the minimum fill-in ordering problem is NP-complete and fill-in is implicit in the sparsity pattern, graph-theoretic heuristics are used. Existing reinforcement learning methods either ignore sparsity patterns--missing the global fill-in--or lack local exact fill-in feedback. We propose a graph policy optimization method, modeling fill-ins from global and local views: both the policy and value networks use a multi-hop graph neural backbone to embed global"},"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":"2605.17362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T10:07:23Z","cross_cats_sorted":[],"title_canon_sha256":"fa6a01babdc594e20c113fe3e99ea5b7d60580e1a746f30687eb41adea117d9d","abstract_canon_sha256":"11c3a73f5b54da6ab4d2d55c4949f809e51d272aeab6ff93e84cce5d69f0c6e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:54.418147Z","signature_b64":"q5jVrfuE08MIpPNURX2qUp4cYfkBoK25fQB/7Rr7n5uKtYDy4eoxMGaCRGekMSrbAyL8MQkD8dRBf9WRAqSrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78c35eaff6d4ab59323c8feeb271eff06b1f389efda0bbf17dbcbbc3af9273fd","last_reissued_at":"2026-05-20T00:03:54.417248Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:54.417248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Fill-in Reduction Ordering via Graph Policy Optimization for Sparse Matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huiyuan Li, Shuzi Niu, Tao Yuan, Wenjia Wu, Ziwei Li","submitted_at":"2026-05-17T10:07:23Z","abstract_excerpt":"Matrix reordering in large sparse solvers seeks a permutation that minimizes factorization fill-in to reduce memory and computation. Because the minimum fill-in ordering problem is NP-complete and fill-in is implicit in the sparsity pattern, graph-theoretic heuristics are used. Existing reinforcement learning methods either ignore sparsity patterns--missing the global fill-in--or lack local exact fill-in feedback. We propose a graph policy optimization method, modeling fill-ins from global and local views: both the policy and value networks use a multi-hop graph neural backbone to embed global"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17362","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/2605.17362/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.785066Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.719779Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e2329a1d64337e65766263ec745788cd751629c5c7a7e665001ebe36b8bf94d8"},"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":"2605.17362","created_at":"2026-05-20T00:03:54.417422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17362v1","created_at":"2026-05-20T00:03:54.417422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17362","created_at":"2026-05-20T00:03:54.417422+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDBV5L7W2SVV","created_at":"2026-05-20T00:03:54.417422+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDBV5L7W2SVVSMR4","created_at":"2026-05-20T00:03:54.417422+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDBV5L7W","created_at":"2026-05-20T00:03:54.417422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17362","citing_title":"Learning Fill-in Reduction Ordering via Graph Policy Optimization for Sparse Matrices","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B","json":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B.json","graph_json":"https://pith.science/api/pith-number/PDBV5L7W2SVVSMR4R7XLE4PP6B/graph.json","events_json":"https://pith.science/api/pith-number/PDBV5L7W2SVVSMR4R7XLE4PP6B/events.json","paper":"https://pith.science/paper/PDBV5L7W"},"agent_actions":{"view_html":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B","download_json":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B.json","view_paper":"https://pith.science/paper/PDBV5L7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17362&json=true","fetch_graph":"https://pith.science/api/pith-number/PDBV5L7W2SVVSMR4R7XLE4PP6B/graph.json","fetch_events":"https://pith.science/api/pith-number/PDBV5L7W2SVVSMR4R7XLE4PP6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B/action/storage_attestation","attest_author":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B/action/author_attestation","sign_citation":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B/action/citation_signature","submit_replication":"https://pith.science/pith/PDBV5L7W2SVVSMR4R7XLE4PP6B/action/replication_record"}},"created_at":"2026-05-20T00:03:54.417422+00:00","updated_at":"2026-05-20T00:03:54.417422+00:00"}