{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24X4CI5GL7FBTCMPEQJTMKWTQF","short_pith_number":"pith:24X4CI5G","schema_version":"1.0","canonical_sha256":"d72fc123a65fca19898f2413362ad381417140064177631e88c671fd678b12a4","source":{"kind":"arxiv","id":"2507.00880","version":1},"attestation_state":"computed","paper":{"title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haokui Zhang, Ruihan Xu, Shiliang Zhang, Wei Zeng, Yaowei Wang","submitted_at":"2025-07-01T15:46:18Z","abstract_excerpt":"The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and transformers have shown promising performance in representing neural architectures. However, each of both methods has its disadvantages. GNNs lack the capabilities to represent complicated features, while transformers face poor generalization when the depth of architecture grows. To mitigate the above issues, we rethink neural architecture topology and show that sibling nodes are "},"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":"2507.00880","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T15:46:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"20d6b6052fe0e60bc6d17d46e9561e9492880930e6dad5a1a07c0ab6eb718076","abstract_canon_sha256":"03a4f6f8d3a8d6680a509c7c3ddf420fd8f841d0c7981194646e238dd13c1b22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:16.596176Z","signature_b64":"odVQVBRZ6CuwIb0K2o/Y+v/GwGTIxdy24pVmsGe8xK+2NGQAfkIHEgxyi2whqJve1xlOXoFGWkMukGZ6dnujBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d72fc123a65fca19898f2413362ad381417140064177631e88c671fd678b12a4","last_reissued_at":"2026-07-05T11:30:16.595594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:16.595594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NN-Former: Rethinking Graph Structure in Neural Architecture Representation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haokui Zhang, Ruihan Xu, Shiliang Zhang, Wei Zeng, Yaowei Wang","submitted_at":"2025-07-01T15:46:18Z","abstract_excerpt":"The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and transformers have shown promising performance in representing neural architectures. However, each of both methods has its disadvantages. GNNs lack the capabilities to represent complicated features, while transformers face poor generalization when the depth of architecture grows. To mitigate the above issues, we rethink neural architecture topology and show that sibling nodes are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00880","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/2507.00880/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":"2507.00880","created_at":"2026-07-05T11:30:16.595663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00880v1","created_at":"2026-07-05T11:30:16.595663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00880","created_at":"2026-07-05T11:30:16.595663+00:00"},{"alias_kind":"pith_short_12","alias_value":"24X4CI5GL7FB","created_at":"2026-07-05T11:30:16.595663+00:00"},{"alias_kind":"pith_short_16","alias_value":"24X4CI5GL7FBTCMP","created_at":"2026-07-05T11:30:16.595663+00:00"},{"alias_kind":"pith_short_8","alias_value":"24X4CI5G","created_at":"2026-07-05T11:30:16.595663+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/24X4CI5GL7FBTCMPEQJTMKWTQF","json":"https://pith.science/pith/24X4CI5GL7FBTCMPEQJTMKWTQF.json","graph_json":"https://pith.science/api/pith-number/24X4CI5GL7FBTCMPEQJTMKWTQF/graph.json","events_json":"https://pith.science/api/pith-number/24X4CI5GL7FBTCMPEQJTMKWTQF/events.json","paper":"https://pith.science/paper/24X4CI5G"},"agent_actions":{"view_html":"https://pith.science/pith/24X4CI5GL7FBTCMPEQJTMKWTQF","download_json":"https://pith.science/pith/24X4CI5GL7FBTCMPEQJTMKWTQF.json","view_paper":"https://pith.science/paper/24X4CI5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00880&json=true","fetch_graph":"https://pith.science/api/pith-number/24X4CI5GL7FBTCMPEQJTMKWTQF/graph.json","fetch_events":"https://pith.science/api/pith-number/24X4CI5GL7FBTCMPEQJTMKWTQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24X4CI5GL7FBTCMPEQJTMKWTQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24X4CI5GL7FBTCMPEQJTMKWTQF/action/storage_attestation","attest_author":"https://pith.science/pith/24X4CI5GL7FBTCMPEQJTMKWTQF/action/author_attestation","sign_citation":"https://pith.science/pith/24X4CI5GL7FBTCMPEQJTMKWTQF/action/citation_signature","submit_replication":"https://pith.science/pith/24X4CI5GL7FBTCMPEQJTMKWTQF/action/replication_record"}},"created_at":"2026-07-05T11:30:16.595663+00:00","updated_at":"2026-07-05T11:30:16.595663+00:00"}