{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DNGA7CSQQHHXZNBZ42SA3NLPYE","short_pith_number":"pith:DNGA7CSQ","schema_version":"1.0","canonical_sha256":"1b4c0f8a5081cf7cb439e6a40db56fc10e1d48c07dd456d58271d3c2816ed359","source":{"kind":"arxiv","id":"1906.01550","version":1},"attestation_state":"computed","paper":{"title":"Towards Task and Architecture-Independent Generalization Gap Predictors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hanna Mazzawi, Javier Gonzalvo, Scott Yak","submitted_at":"2019-06-04T16:10:15Z","abstract_excerpt":"Can we use deep learning to predict when deep learning works? Our results suggest the affirmative. We created a dataset by training 13,500 neural networks with different architectures, on different variations of spiral datasets, and using different optimization parameters. We used this dataset to train task-independent and architecture-independent generalization gap predictors for those neural networks. We extend Jiang et al. (2018) to also use DNNs and RNNs and show that they outperform the linear model, obtaining $R^2=0.965$. We also show results for architecture-independent, task-independen"},"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":"1906.01550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2019-06-04T16:10:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b03c4c0fa8c3ab0d16c207c7e313292a292398cd42e81d62676019229aec64b3","abstract_canon_sha256":"fde9451b67c104188aeb954824223ba7463beffa312226b39cb68f8e52d190dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:16.181158Z","signature_b64":"AlB/S7Kyo8juVxcwKNfux9UmchvhAciUVBg/KpuirSMi7ccE3HFr9xI/44uGBB/3GoltARHEF/VyKd8ecsprAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b4c0f8a5081cf7cb439e6a40db56fc10e1d48c07dd456d58271d3c2816ed359","last_reissued_at":"2026-05-17T23:44:16.180574Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:16.180574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Task and Architecture-Independent Generalization Gap Predictors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hanna Mazzawi, Javier Gonzalvo, Scott Yak","submitted_at":"2019-06-04T16:10:15Z","abstract_excerpt":"Can we use deep learning to predict when deep learning works? Our results suggest the affirmative. We created a dataset by training 13,500 neural networks with different architectures, on different variations of spiral datasets, and using different optimization parameters. We used this dataset to train task-independent and architecture-independent generalization gap predictors for those neural networks. We extend Jiang et al. (2018) to also use DNNs and RNNs and show that they outperform the linear model, obtaining $R^2=0.965$. We also show results for architecture-independent, task-independen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01550","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":""},"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":"1906.01550","created_at":"2026-05-17T23:44:16.180664+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01550v1","created_at":"2026-05-17T23:44:16.180664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01550","created_at":"2026-05-17T23:44:16.180664+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNGA7CSQQHHX","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNGA7CSQQHHXZNBZ","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNGA7CSQ","created_at":"2026-05-18T12:33:15.570797+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/DNGA7CSQQHHXZNBZ42SA3NLPYE","json":"https://pith.science/pith/DNGA7CSQQHHXZNBZ42SA3NLPYE.json","graph_json":"https://pith.science/api/pith-number/DNGA7CSQQHHXZNBZ42SA3NLPYE/graph.json","events_json":"https://pith.science/api/pith-number/DNGA7CSQQHHXZNBZ42SA3NLPYE/events.json","paper":"https://pith.science/paper/DNGA7CSQ"},"agent_actions":{"view_html":"https://pith.science/pith/DNGA7CSQQHHXZNBZ42SA3NLPYE","download_json":"https://pith.science/pith/DNGA7CSQQHHXZNBZ42SA3NLPYE.json","view_paper":"https://pith.science/paper/DNGA7CSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01550&json=true","fetch_graph":"https://pith.science/api/pith-number/DNGA7CSQQHHXZNBZ42SA3NLPYE/graph.json","fetch_events":"https://pith.science/api/pith-number/DNGA7CSQQHHXZNBZ42SA3NLPYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNGA7CSQQHHXZNBZ42SA3NLPYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNGA7CSQQHHXZNBZ42SA3NLPYE/action/storage_attestation","attest_author":"https://pith.science/pith/DNGA7CSQQHHXZNBZ42SA3NLPYE/action/author_attestation","sign_citation":"https://pith.science/pith/DNGA7CSQQHHXZNBZ42SA3NLPYE/action/citation_signature","submit_replication":"https://pith.science/pith/DNGA7CSQQHHXZNBZ42SA3NLPYE/action/replication_record"}},"created_at":"2026-05-17T23:44:16.180664+00:00","updated_at":"2026-05-17T23:44:16.180664+00:00"}