{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GUVTGCO5AHJBVAUHHQEP45DCMV","short_pith_number":"pith:GUVTGCO5","schema_version":"1.0","canonical_sha256":"352b3309dd01d21a82873c08fe74626553e07e60efa1a5aa83961c1a09d125da","source":{"kind":"arxiv","id":"2509.21886","version":3},"attestation_state":"computed","paper":{"title":"TRACE: Learning to Compute on Circuit Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaying Zhu, Jingyi Zhou, Qiang Xu, Ziyang Zheng","submitted_at":"2025-09-26T05:22:32Z","abstract_excerpt":"Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed assumption, central to mainstream message passing neural networks (MPNNs) and their conventional Transformer-based counterparts, prevents models from capturing the position-aware, hierarchical nature of computation. To resolve this, we introduce TRACE, a new paradigm built on an architecturally sound backbone and a principled learning objective. First, TRACE employs"},"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":"2509.21886","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-26T05:22:32Z","cross_cats_sorted":[],"title_canon_sha256":"60377d88dc28bd72de3d6ea87672ac18f709775e4944fca01a2a97f1c71e7478","abstract_canon_sha256":"8118094a1527fbd751671a1ed800f9369073bd06b2d3bbc63d9b983591e5ba5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:51.259344Z","signature_b64":"CzbffnMaPGbTByyWby0d7PzqmTekjjTy6mpK+JBmdebElYcD5Bu52xJnWMcT/PVKZgUGKRuH4roC3R9Kgd/GDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"352b3309dd01d21a82873c08fe74626553e07e60efa1a5aa83961c1a09d125da","last_reissued_at":"2026-06-19T16:09:51.258950Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:51.258950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRACE: Learning to Compute on Circuit Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaying Zhu, Jingyi Zhou, Qiang Xu, Ziyang Zheng","submitted_at":"2025-09-26T05:22:32Z","abstract_excerpt":"Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed assumption, central to mainstream message passing neural networks (MPNNs) and their conventional Transformer-based counterparts, prevents models from capturing the position-aware, hierarchical nature of computation. To resolve this, we introduce TRACE, a new paradigm built on an architecturally sound backbone and a principled learning objective. First, TRACE employs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.21886","kind":"arxiv","version":3},"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/2509.21886/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":"2509.21886","created_at":"2026-06-19T16:09:51.259008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.21886v3","created_at":"2026-06-19T16:09:51.259008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.21886","created_at":"2026-06-19T16:09:51.259008+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUVTGCO5AHJB","created_at":"2026-06-19T16:09:51.259008+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUVTGCO5AHJBVAUH","created_at":"2026-06-19T16:09:51.259008+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUVTGCO5","created_at":"2026-06-19T16:09:51.259008+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/GUVTGCO5AHJBVAUHHQEP45DCMV","json":"https://pith.science/pith/GUVTGCO5AHJBVAUHHQEP45DCMV.json","graph_json":"https://pith.science/api/pith-number/GUVTGCO5AHJBVAUHHQEP45DCMV/graph.json","events_json":"https://pith.science/api/pith-number/GUVTGCO5AHJBVAUHHQEP45DCMV/events.json","paper":"https://pith.science/paper/GUVTGCO5"},"agent_actions":{"view_html":"https://pith.science/pith/GUVTGCO5AHJBVAUHHQEP45DCMV","download_json":"https://pith.science/pith/GUVTGCO5AHJBVAUHHQEP45DCMV.json","view_paper":"https://pith.science/paper/GUVTGCO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.21886&json=true","fetch_graph":"https://pith.science/api/pith-number/GUVTGCO5AHJBVAUHHQEP45DCMV/graph.json","fetch_events":"https://pith.science/api/pith-number/GUVTGCO5AHJBVAUHHQEP45DCMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUVTGCO5AHJBVAUHHQEP45DCMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUVTGCO5AHJBVAUHHQEP45DCMV/action/storage_attestation","attest_author":"https://pith.science/pith/GUVTGCO5AHJBVAUHHQEP45DCMV/action/author_attestation","sign_citation":"https://pith.science/pith/GUVTGCO5AHJBVAUHHQEP45DCMV/action/citation_signature","submit_replication":"https://pith.science/pith/GUVTGCO5AHJBVAUHHQEP45DCMV/action/replication_record"}},"created_at":"2026-06-19T16:09:51.259008+00:00","updated_at":"2026-06-19T16:09:51.259008+00:00"}