{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:F7BFWG2N45WRLP2AZGV3K2R64V","short_pith_number":"pith:F7BFWG2N","canonical_record":{"source":{"id":"2110.04622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-09T18:16:23Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"f881ea4fee2beba01233be7ac841ac16b281a63019efa31e949caacc72903c38","abstract_canon_sha256":"f22a8a3b72262d366b9fba8f1380a58b74bbb00f70a4696c2a20fd5766350884"},"schema_version":"1.0"},"canonical_sha256":"2fc25b1b4de76d15bf40c9abb56a3ee552562eeff4f9c1df3ecde2abfcbd31d9","source":{"kind":"arxiv","id":"2110.04622","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04622","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04622v1","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04622","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"pith_short_12","alias_value":"F7BFWG2N45WR","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"pith_short_16","alias_value":"F7BFWG2N45WRLP2A","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"pith_short_8","alias_value":"F7BFWG2N","created_at":"2026-07-05T03:21:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:F7BFWG2N45WRLP2AZGV3K2R64V","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-09T18:16:23Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"f881ea4fee2beba01233be7ac841ac16b281a63019efa31e949caacc72903c38","abstract_canon_sha256":"f22a8a3b72262d366b9fba8f1380a58b74bbb00f70a4696c2a20fd5766350884"},"schema_version":"1.0"},"canonical_sha256":"2fc25b1b4de76d15bf40c9abb56a3ee552562eeff4f9c1df3ecde2abfcbd31d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:19.391633Z","signature_b64":"o8nrIImHAqNmk9l6bIaogXu7EA/aCgeDJqDwUHDuAQ2sT/AaHG75o0sisf/yAWUt0LgJf3Om9FFjiM4z54PBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fc25b1b4de76d15bf40c9abb56a3ee552562eeff4f9c1df3ecde2abfcbd31d9","last_reissued_at":"2026-07-05T03:21:19.391209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:19.391209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04622","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:21:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"avmkbIIEA5X9TRP4JIM0A7G3HS34nHzfOj0Y7od4/LdQTldY0OIzX2wN/4Uh16AECeiB2WYjxDogtDw5tl0BBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:13:22.383881Z"},"content_sha256":"4ac1730d42fe30ee301f6dd28afeeb918661f60751110d53779b3e484dbf363c","schema_version":"1.0","event_id":"sha256:4ac1730d42fe30ee301f6dd28afeeb918661f60751110d53779b3e484dbf363c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:F7BFWG2N45WRLP2AZGV3K2R64V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ruizhe Zhang, Shuo Yang, Zhao Song","submitted_at":"2021-10-09T18:16:23Z","abstract_excerpt":"Deep neural networks have achieved impressive performance in many areas. Designing a fast and provable method for training neural networks is a fundamental question in machine learning.\n  The classical training method requires paying $\\Omega(mnd)$ cost for both forward computation and backward computation, where $m$ is the width of the neural network, and we are given $n$ training points in $d$-dimensional space. In this paper, we propose two novel preprocessing ideas to bypass this $\\Omega(mnd)$ barrier:\n  $\\bullet$ First, by preprocessing the initial weights of the neural networks, we can tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04622","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/2110.04622/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:21:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kFggmt+cJBvEf+rxFXcV2hklxHNh0wuu0Pq06a/gzKiFKnWIUZr1A7IRmIjXl7MBhEWQbLZaAr0iyYYeDejyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:13:22.384385Z"},"content_sha256":"123a50108fe3292d999c7b6f86df1912cab78bf87e8b950428e105567873510d","schema_version":"1.0","event_id":"sha256:123a50108fe3292d999c7b6f86df1912cab78bf87e8b950428e105567873510d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7BFWG2N45WRLP2AZGV3K2R64V/bundle.json","state_url":"https://pith.science/pith/F7BFWG2N45WRLP2AZGV3K2R64V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7BFWG2N45WRLP2AZGV3K2R64V/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T05:13:22Z","links":{"resolver":"https://pith.science/pith/F7BFWG2N45WRLP2AZGV3K2R64V","bundle":"https://pith.science/pith/F7BFWG2N45WRLP2AZGV3K2R64V/bundle.json","state":"https://pith.science/pith/F7BFWG2N45WRLP2AZGV3K2R64V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7BFWG2N45WRLP2AZGV3K2R64V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:F7BFWG2N45WRLP2AZGV3K2R64V","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f22a8a3b72262d366b9fba8f1380a58b74bbb00f70a4696c2a20fd5766350884","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-09T18:16:23Z","title_canon_sha256":"f881ea4fee2beba01233be7ac841ac16b281a63019efa31e949caacc72903c38"},"schema_version":"1.0","source":{"id":"2110.04622","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04622","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04622v1","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04622","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"pith_short_12","alias_value":"F7BFWG2N45WR","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"pith_short_16","alias_value":"F7BFWG2N45WRLP2A","created_at":"2026-07-05T03:21:19Z"},{"alias_kind":"pith_short_8","alias_value":"F7BFWG2N","created_at":"2026-07-05T03:21:19Z"}],"graph_snapshots":[{"event_id":"sha256:123a50108fe3292d999c7b6f86df1912cab78bf87e8b950428e105567873510d","target":"graph","created_at":"2026-07-05T03:21:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.04622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks have achieved impressive performance in many areas. Designing a fast and provable method for training neural networks is a fundamental question in machine learning.\n  The classical training method requires paying $\\Omega(mnd)$ cost for both forward computation and backward computation, where $m$ is the width of the neural network, and we are given $n$ training points in $d$-dimensional space. In this paper, we propose two novel preprocessing ideas to bypass this $\\Omega(mnd)$ barrier:\n  $\\bullet$ First, by preprocessing the initial weights of the neural networks, we can tr","authors_text":"Ruizhe Zhang, Shuo Yang, Zhao Song","cross_cats":["cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-09T18:16:23Z","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04622","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4ac1730d42fe30ee301f6dd28afeeb918661f60751110d53779b3e484dbf363c","target":"record","created_at":"2026-07-05T03:21:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f22a8a3b72262d366b9fba8f1380a58b74bbb00f70a4696c2a20fd5766350884","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-09T18:16:23Z","title_canon_sha256":"f881ea4fee2beba01233be7ac841ac16b281a63019efa31e949caacc72903c38"},"schema_version":"1.0","source":{"id":"2110.04622","kind":"arxiv","version":1}},"canonical_sha256":"2fc25b1b4de76d15bf40c9abb56a3ee552562eeff4f9c1df3ecde2abfcbd31d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fc25b1b4de76d15bf40c9abb56a3ee552562eeff4f9c1df3ecde2abfcbd31d9","first_computed_at":"2026-07-05T03:21:19.391209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:19.391209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o8nrIImHAqNmk9l6bIaogXu7EA/aCgeDJqDwUHDuAQ2sT/AaHG75o0sisf/yAWUt0LgJf3Om9FFjiM4z54PBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:19.391633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04622","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ac1730d42fe30ee301f6dd28afeeb918661f60751110d53779b3e484dbf363c","sha256:123a50108fe3292d999c7b6f86df1912cab78bf87e8b950428e105567873510d"],"state_sha256":"c9ea6a50f573497304106d8de43e0eea2ad903a4a167c12fff421646d688b336"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bPwcdYjF8iVpe/5ZUGhnOlR2OPW8WvPNtKiNS1K4gRUSV83LsL2XhdnlWP3C1wPrMvoNhPhHBrd7GipqkrOcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:13:22.387949Z","bundle_sha256":"3c66d979e66ecd008735058c3585e4fd9dfa7e145fc69789ea8e33202ea3111c"}}