{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:YEX6ZT5KJL2MNIDJOW4WIB47VM","short_pith_number":"pith:YEX6ZT5K","canonical_record":{"source":{"id":"2006.07928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T15:26:07Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"6d036f7603273f73c63b939328d662bcc141287e095dab7739901f0a03f1ecab","abstract_canon_sha256":"bcd2e355e241c056595dc04eb9c5cedc5b6b784f312a2ae88ea365325d3f328b"},"schema_version":"1.0"},"canonical_sha256":"c12feccfaa4af4c6a06975b964079fab22798e8eabf1f500369e1729d645b6c7","source":{"kind":"arxiv","id":"2006.07928","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07928","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07928v2","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07928","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"YEX6ZT5KJL2M","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"YEX6ZT5KJL2MNIDJ","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"YEX6ZT5K","created_at":"2026-07-05T01:27:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:YEX6ZT5KJL2MNIDJOW4WIB47VM","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T15:26:07Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"6d036f7603273f73c63b939328d662bcc141287e095dab7739901f0a03f1ecab","abstract_canon_sha256":"bcd2e355e241c056595dc04eb9c5cedc5b6b784f312a2ae88ea365325d3f328b"},"schema_version":"1.0"},"canonical_sha256":"c12feccfaa4af4c6a06975b964079fab22798e8eabf1f500369e1729d645b6c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:24.338119Z","signature_b64":"dJjaLCH9hI/CEPrBiLsDDuxtS0X/XhFLr/e1h75w1dtMhjL1BRHR7EuVVnM0Iz3Wegd7Ei0hO5XMl7cxWBOnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c12feccfaa4af4c6a06975b964079fab22798e8eabf1f500369e1729d645b6c7","last_reissued_at":"2026-07-05T01:27:24.337714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:24.337714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07928","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:27:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NBdyIRp4jM5HkiH7hUZOYRuP4fkKJhNsFcNPTU0Lk1WhmYuzvFmoTUItU+zwPeN0XMx95Qvga+Ku5rpw3F3WDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T14:17:02.459859Z"},"content_sha256":"43354e6bb47f81a4af9bb39530ae2ac84eaa0ae559689cf56d678ff1e1e86c50","schema_version":"1.0","event_id":"sha256:43354e6bb47f81a4af9bb39530ae2ac84eaa0ae559689cf56d678ff1e1e86c50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:YEX6ZT5KJL2MNIDJOW4WIB47VM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Global Convergence of Sobolev Training for Overparameterized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jorio Cocola, Paul Hand","submitted_at":"2020-06-14T15:26:07Z","abstract_excerpt":"Sobolev loss is used when training a network to approximate the values and derivatives of a target function at a prescribed set of input points. Recent works have demonstrated its successful applications in various tasks such as distillation or synthetic gradient prediction. In this work we prove that an overparameterized two-layer relu neural network trained on the Sobolev loss with gradient flow from random initialization can fit any given function values and any given directional derivatives, under a separation condition on the input data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07928","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/2006.07928/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":"2026-07-05T01:27:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MKqHBV8DldL5Choc9R7G7J+AXr9gXirZ/Jr+TBFujQ30iEPROGw1EZcOPlLd3aq8+/r5LFQfMz557LrhtEfFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T14:17:02.460298Z"},"content_sha256":"bb943e47d0f938ec0e80f1ef09616d26810cc60ba4ae0a538ec05ee65f888ddb","schema_version":"1.0","event_id":"sha256:bb943e47d0f938ec0e80f1ef09616d26810cc60ba4ae0a538ec05ee65f888ddb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEX6ZT5KJL2MNIDJOW4WIB47VM/bundle.json","state_url":"https://pith.science/pith/YEX6ZT5KJL2MNIDJOW4WIB47VM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEX6ZT5KJL2MNIDJOW4WIB47VM/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":"2026-07-11T14:17:02Z","links":{"resolver":"https://pith.science/pith/YEX6ZT5KJL2MNIDJOW4WIB47VM","bundle":"https://pith.science/pith/YEX6ZT5KJL2MNIDJOW4WIB47VM/bundle.json","state":"https://pith.science/pith/YEX6ZT5KJL2MNIDJOW4WIB47VM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEX6ZT5KJL2MNIDJOW4WIB47VM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YEX6ZT5KJL2MNIDJOW4WIB47VM","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":"bcd2e355e241c056595dc04eb9c5cedc5b6b784f312a2ae88ea365325d3f328b","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T15:26:07Z","title_canon_sha256":"6d036f7603273f73c63b939328d662bcc141287e095dab7739901f0a03f1ecab"},"schema_version":"1.0","source":{"id":"2006.07928","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07928","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07928v2","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07928","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"YEX6ZT5KJL2M","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"YEX6ZT5KJL2MNIDJ","created_at":"2026-07-05T01:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"YEX6ZT5K","created_at":"2026-07-05T01:27:24Z"}],"graph_snapshots":[{"event_id":"sha256:bb943e47d0f938ec0e80f1ef09616d26810cc60ba4ae0a538ec05ee65f888ddb","target":"graph","created_at":"2026-07-05T01:27:24Z","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/2006.07928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sobolev loss is used when training a network to approximate the values and derivatives of a target function at a prescribed set of input points. Recent works have demonstrated its successful applications in various tasks such as distillation or synthetic gradient prediction. In this work we prove that an overparameterized two-layer relu neural network trained on the Sobolev loss with gradient flow from random initialization can fit any given function values and any given directional derivatives, under a separation condition on the input data.","authors_text":"Jorio Cocola, Paul Hand","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T15:26:07Z","title":"Global Convergence of Sobolev Training for Overparameterized Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07928","kind":"arxiv","version":2},"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":"sha256:43354e6bb47f81a4af9bb39530ae2ac84eaa0ae559689cf56d678ff1e1e86c50","target":"record","created_at":"2026-07-05T01:27:24Z","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":"bcd2e355e241c056595dc04eb9c5cedc5b6b784f312a2ae88ea365325d3f328b","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T15:26:07Z","title_canon_sha256":"6d036f7603273f73c63b939328d662bcc141287e095dab7739901f0a03f1ecab"},"schema_version":"1.0","source":{"id":"2006.07928","kind":"arxiv","version":2}},"canonical_sha256":"c12feccfaa4af4c6a06975b964079fab22798e8eabf1f500369e1729d645b6c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c12feccfaa4af4c6a06975b964079fab22798e8eabf1f500369e1729d645b6c7","first_computed_at":"2026-07-05T01:27:24.337714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:24.337714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dJjaLCH9hI/CEPrBiLsDDuxtS0X/XhFLr/e1h75w1dtMhjL1BRHR7EuVVnM0Iz3Wegd7Ei0hO5XMl7cxWBOnAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:24.338119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07928","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43354e6bb47f81a4af9bb39530ae2ac84eaa0ae559689cf56d678ff1e1e86c50","sha256:bb943e47d0f938ec0e80f1ef09616d26810cc60ba4ae0a538ec05ee65f888ddb"],"state_sha256":"abd4f5894b064b68a10622aef9f5d6e66e16258c01adfba43cf4cad8107374dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6vBuAab0WgmSdv2DiB5Rl/Sq+YTeedm2SxfsNUjaWUDNCWytqzNoVjTrG6xLRpOXeqX9EXkjrkPrGuoYWYUNAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T14:17:02.463258Z","bundle_sha256":"163360df897da5eaa03f6dc287f18ac993e1bd5e3331f725b65d548058fb7903"}}