{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DARB5IKOENAW7Z2QESTN2ZS6CZ","short_pith_number":"pith:DARB5IKO","schema_version":"1.0","canonical_sha256":"18221ea14e23416fe75024a6dd665e16733b8d9ca72ec8ac06fc4aa62e24e4b7","source":{"kind":"arxiv","id":"2404.16551","version":2},"attestation_state":"computed","paper":{"title":"Surprisingly Strong Performance Prediction with Neural Graph Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Gabriela Kadlecov\\'a, Jovita Lukasik, Mahmoud Safari, Martin Pil\\'at, Petra Vidnerov\\'a, Roman Neruda","submitted_at":"2024-04-25T12:07:41Z","abstract_excerpt":"Performance prediction has been a key part of the neural architecture search (NAS) process, allowing to speed up NAS algorithms by avoiding resource-consuming network training. Although many performance predictors correlate well with ground truth performance, they require training data in the form of trained networks. Recently, zero-cost proxies have been proposed as an efficient method to estimate network performance without any training. However, they are still poorly understood, exhibit biases with network properties, and their performance is limited. Inspired by the drawbacks of zero-cost "},"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":"2404.16551","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T12:07:41Z","cross_cats_sorted":[],"title_canon_sha256":"97850f76dbd37d8c61319448a4c94a0b91b0ae05936a36b8275a71085f60458a","abstract_canon_sha256":"7c9f510fd2a66fb30c9315ab1dbe82adbc5c33563868b0b66618d7a23bf9b1d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:49.580163Z","signature_b64":"Dqf4l31cXJO5JPaC+bAonlMMjWrrA/AvKdiY44AhZy6Fvr/2M9JKCqmENgt18XOsrQtLG6Km17x675y3ZAxRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18221ea14e23416fe75024a6dd665e16733b8d9ca72ec8ac06fc4aa62e24e4b7","last_reissued_at":"2026-07-05T08:54:49.579335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:49.579335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surprisingly Strong Performance Prediction with Neural Graph Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Gabriela Kadlecov\\'a, Jovita Lukasik, Mahmoud Safari, Martin Pil\\'at, Petra Vidnerov\\'a, Roman Neruda","submitted_at":"2024-04-25T12:07:41Z","abstract_excerpt":"Performance prediction has been a key part of the neural architecture search (NAS) process, allowing to speed up NAS algorithms by avoiding resource-consuming network training. Although many performance predictors correlate well with ground truth performance, they require training data in the form of trained networks. Recently, zero-cost proxies have been proposed as an efficient method to estimate network performance without any training. However, they are still poorly understood, exhibit biases with network properties, and their performance is limited. Inspired by the drawbacks of zero-cost "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16551","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/2404.16551/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":"2404.16551","created_at":"2026-07-05T08:54:49.579393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16551v2","created_at":"2026-07-05T08:54:49.579393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16551","created_at":"2026-07-05T08:54:49.579393+00:00"},{"alias_kind":"pith_short_12","alias_value":"DARB5IKOENAW","created_at":"2026-07-05T08:54:49.579393+00:00"},{"alias_kind":"pith_short_16","alias_value":"DARB5IKOENAW7Z2Q","created_at":"2026-07-05T08:54:49.579393+00:00"},{"alias_kind":"pith_short_8","alias_value":"DARB5IKO","created_at":"2026-07-05T08:54:49.579393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26422","citing_title":"STLGT: A Scalable Trace-Based Linear Graph Transformer for Tail Latency Prediction in Microservices","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ","json":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ.json","graph_json":"https://pith.science/api/pith-number/DARB5IKOENAW7Z2QESTN2ZS6CZ/graph.json","events_json":"https://pith.science/api/pith-number/DARB5IKOENAW7Z2QESTN2ZS6CZ/events.json","paper":"https://pith.science/paper/DARB5IKO"},"agent_actions":{"view_html":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ","download_json":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ.json","view_paper":"https://pith.science/paper/DARB5IKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16551&json=true","fetch_graph":"https://pith.science/api/pith-number/DARB5IKOENAW7Z2QESTN2ZS6CZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DARB5IKOENAW7Z2QESTN2ZS6CZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ/action/storage_attestation","attest_author":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ/action/author_attestation","sign_citation":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ/action/citation_signature","submit_replication":"https://pith.science/pith/DARB5IKOENAW7Z2QESTN2ZS6CZ/action/replication_record"}},"created_at":"2026-07-05T08:54:49.579393+00:00","updated_at":"2026-07-05T08:54:49.579393+00:00"}