{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UAP4XNP5WN5SCOTLVXG4H53XLK","short_pith_number":"pith:UAP4XNP5","schema_version":"1.0","canonical_sha256":"a01fcbb5fdb37b213a6badcdc3f7775aaf0a94e0b2e614809c04d2917fbeddda","source":{"kind":"arxiv","id":"2604.23658","version":2},"attestation_state":"computed","paper":{"title":"FlowPlace: Flow Matching for Chip Placement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FlowPlace applies flow matching to chip placement to deliver overlap-free layouts with superior PPA metrics and 10-50 times faster sampling than diffusion models.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Chao Qian, Chengrui Gao, Chenjian Ding, Ke Xue, Mingxuan Yuan, Peng Xie, Ruo-Tong Chen, Siyuan Xu, Yunqi Shi","submitted_at":"2026-04-26T11:25:17Z","abstract_excerpt":"Chip placement plays an important role in physical design. While generative models like diffusion models offer promising learning-based solutions, current methods have the following limitations: they use random synthetic data for pre-training, require long sampling times, and often result in overlaps due to their dependence on gradient-based solvers during the sampling process. To overcome these issues, we propose FlowPlace, which features mask-guided synthetic data generation, flow-based efficient training with flexible prior injection, and hard constraint sampling for overlap-free layouts. E"},"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":"2604.23658","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-04-26T11:25:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fef849e33146f4cef892a06f531c6cc1611e1d30717f2d314d98251ffe43b597","abstract_canon_sha256":"d7efe8e40cad1e11e0620e801f22b107636e56bd4ee21854ff8a926dac451ac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:41.528245Z","signature_b64":"m0iMGwNN6rQtqT1d8kpXEAZgxQZ8jGppfpuveYS/5DXfxK0m1mcJwcOuU0djXyi/y+YBukKvb0Pdwn4w+5V9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a01fcbb5fdb37b213a6badcdc3f7775aaf0a94e0b2e614809c04d2917fbeddda","last_reissued_at":"2026-06-02T03:04:41.527847Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:41.527847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowPlace: Flow Matching for Chip Placement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FlowPlace applies flow matching to chip placement to deliver overlap-free layouts with superior PPA metrics and 10-50 times faster sampling than diffusion models.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Chao Qian, Chengrui Gao, Chenjian Ding, Ke Xue, Mingxuan Yuan, Peng Xie, Ruo-Tong Chen, Siyuan Xu, Yunqi Shi","submitted_at":"2026-04-26T11:25:17Z","abstract_excerpt":"Chip placement plays an important role in physical design. While generative models like diffusion models offer promising learning-based solutions, current methods have the following limitations: they use random synthetic data for pre-training, require long sampling times, and often result in overlaps due to their dependence on gradient-based solvers during the sampling process. To overcome these issues, we propose FlowPlace, which features mask-guided synthetic data generation, flow-based efficient training with flexible prior injection, and hard constraint sampling for overlap-free layouts. E"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on OpenROAD and ICCAD 2015 benchmarks show FlowPlace achieves better PPA metrics, 10-50× faster sampling efficiency, and zero overlaps.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That mask-guided synthetic data generation combined with hard constraint sampling will produce valid, high-quality placements that generalize from the tested benchmarks to real industrial chip designs without introducing new failure modes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FlowPlace uses flow matching with mask-guided data and hard constraints to generate faster, overlap-free chip placements with better PPA metrics than diffusion models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FlowPlace applies flow matching to chip placement to deliver overlap-free layouts with superior PPA metrics and 10-50 times faster sampling than diffusion models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a23c7ee0ae5ecc17381cfeb4a8deec03ae7360aa2c3b0f171fee058041ab1a52"},"source":{"id":"2604.23658","kind":"arxiv","version":2},"verdict":{"id":"bba42caa-cb45-4ea4-ba4f-a459b18930d1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T05:03:38.788365Z","strongest_claim":"Experiments on OpenROAD and ICCAD 2015 benchmarks show FlowPlace achieves better PPA metrics, 10-50× faster sampling efficiency, and zero overlaps.","one_line_summary":"FlowPlace uses flow matching with mask-guided data and hard constraints to generate faster, overlap-free chip placements with better PPA metrics than diffusion models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That mask-guided synthetic data generation combined with hard constraint sampling will produce valid, high-quality placements that generalize from the tested benchmarks to real industrial chip designs without introducing new failure modes.","pith_extraction_headline":"FlowPlace applies flow matching to chip placement to deliver overlap-free layouts with superior PPA metrics and 10-50 times faster sampling than diffusion models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.23658/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T08:37:23.696110Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:54:54.082618Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"48cd2dce571f715e8d98c923d4676be141049a60ff81b958d2772d20d6528556"},"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":"2604.23658","created_at":"2026-06-02T03:04:41.527900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.23658v2","created_at":"2026-06-02T03:04:41.527900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23658","created_at":"2026-06-02T03:04:41.527900+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAP4XNP5WN5S","created_at":"2026-06-02T03:04:41.527900+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAP4XNP5WN5SCOTL","created_at":"2026-06-02T03:04:41.527900+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAP4XNP5","created_at":"2026-06-02T03:04:41.527900+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/UAP4XNP5WN5SCOTLVXG4H53XLK","json":"https://pith.science/pith/UAP4XNP5WN5SCOTLVXG4H53XLK.json","graph_json":"https://pith.science/api/pith-number/UAP4XNP5WN5SCOTLVXG4H53XLK/graph.json","events_json":"https://pith.science/api/pith-number/UAP4XNP5WN5SCOTLVXG4H53XLK/events.json","paper":"https://pith.science/paper/UAP4XNP5"},"agent_actions":{"view_html":"https://pith.science/pith/UAP4XNP5WN5SCOTLVXG4H53XLK","download_json":"https://pith.science/pith/UAP4XNP5WN5SCOTLVXG4H53XLK.json","view_paper":"https://pith.science/paper/UAP4XNP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.23658&json=true","fetch_graph":"https://pith.science/api/pith-number/UAP4XNP5WN5SCOTLVXG4H53XLK/graph.json","fetch_events":"https://pith.science/api/pith-number/UAP4XNP5WN5SCOTLVXG4H53XLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAP4XNP5WN5SCOTLVXG4H53XLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAP4XNP5WN5SCOTLVXG4H53XLK/action/storage_attestation","attest_author":"https://pith.science/pith/UAP4XNP5WN5SCOTLVXG4H53XLK/action/author_attestation","sign_citation":"https://pith.science/pith/UAP4XNP5WN5SCOTLVXG4H53XLK/action/citation_signature","submit_replication":"https://pith.science/pith/UAP4XNP5WN5SCOTLVXG4H53XLK/action/replication_record"}},"created_at":"2026-06-02T03:04:41.527900+00:00","updated_at":"2026-06-02T03:04:41.527900+00:00"}