{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PE3PRNOPGHOIHOIKIBZXXLDQMZ","short_pith_number":"pith:PE3PRNOP","schema_version":"1.0","canonical_sha256":"7936f8b5cf31dc83b90a40737bac70667ce81e7d5f52d0a1ace88d5d166835d7","source":{"kind":"arxiv","id":"2403.00012","version":2},"attestation_state":"computed","paper":{"title":"PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Jianye Hao, Junchi Yan, Junjie Ye, Mingxuan Yuan, Ruizhe Zhong, Shixiong Kai, Zhentao Tang","submitted_at":"2024-02-27T02:23:07Z","abstract_excerpt":"Pre-routing timing prediction has been recently studied for evaluating the quality of a candidate cell placement in chip design. It involves directly estimating the timing metrics for both pin-level (slack, slew) and edge-level (net delay, cell delay), without time-consuming routing. However, it often suffers from signal decay and error accumulation due to the long timing paths in large-scale industrial circuits. To address these challenges, we propose a two-stage approach. First, we propose global circuit training to pre-train a graph auto-encoder that learns the global graph embedding from 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":"2403.00012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T02:23:07Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"1115013cd447456ec691d5715ad7a5d8bad7a887fe4cf052a200c673c2768582","abstract_canon_sha256":"f645759e37c61d41b1869d235566dff59b3d90402ebeb71ca1823b087ccb6a5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:55.095170Z","signature_b64":"fh+hia4avkgK+DK5QJlzb7FNBC2zv7OzvD4+4SzNj6vaQ/6jAHzzQ/uFMjpoeOjZyqPmq4lpQU8xp7PESZ8zAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7936f8b5cf31dc83b90a40737bac70667ce81e7d5f52d0a1ace88d5d166835d7","last_reissued_at":"2026-07-05T07:54:55.094651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:55.094651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Jianye Hao, Junchi Yan, Junjie Ye, Mingxuan Yuan, Ruizhe Zhong, Shixiong Kai, Zhentao Tang","submitted_at":"2024-02-27T02:23:07Z","abstract_excerpt":"Pre-routing timing prediction has been recently studied for evaluating the quality of a candidate cell placement in chip design. It involves directly estimating the timing metrics for both pin-level (slack, slew) and edge-level (net delay, cell delay), without time-consuming routing. However, it often suffers from signal decay and error accumulation due to the long timing paths in large-scale industrial circuits. To address these challenges, we propose a two-stage approach. First, we propose global circuit training to pre-train a graph auto-encoder that learns the global graph embedding from c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00012","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/2403.00012/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":"2403.00012","created_at":"2026-07-05T07:54:55.094711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00012v2","created_at":"2026-07-05T07:54:55.094711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00012","created_at":"2026-07-05T07:54:55.094711+00:00"},{"alias_kind":"pith_short_12","alias_value":"PE3PRNOPGHOI","created_at":"2026-07-05T07:54:55.094711+00:00"},{"alias_kind":"pith_short_16","alias_value":"PE3PRNOPGHOIHOIK","created_at":"2026-07-05T07:54:55.094711+00:00"},{"alias_kind":"pith_short_8","alias_value":"PE3PRNOP","created_at":"2026-07-05T07:54:55.094711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03502","citing_title":"Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ","json":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ.json","graph_json":"https://pith.science/api/pith-number/PE3PRNOPGHOIHOIKIBZXXLDQMZ/graph.json","events_json":"https://pith.science/api/pith-number/PE3PRNOPGHOIHOIKIBZXXLDQMZ/events.json","paper":"https://pith.science/paper/PE3PRNOP"},"agent_actions":{"view_html":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ","download_json":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ.json","view_paper":"https://pith.science/paper/PE3PRNOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00012&json=true","fetch_graph":"https://pith.science/api/pith-number/PE3PRNOPGHOIHOIKIBZXXLDQMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PE3PRNOPGHOIHOIKIBZXXLDQMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ/action/storage_attestation","attest_author":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ/action/author_attestation","sign_citation":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ/action/citation_signature","submit_replication":"https://pith.science/pith/PE3PRNOPGHOIHOIKIBZXXLDQMZ/action/replication_record"}},"created_at":"2026-07-05T07:54:55.094711+00:00","updated_at":"2026-07-05T07:54:55.094711+00:00"}