{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EUC524QMZED2SI5NOOGUHBZ6G5","short_pith_number":"pith:EUC524QM","canonical_record":{"source":{"id":"1703.09833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-28T22:47:04Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"7b6a8d0af763104bc7167abca06c2b5dbafc6636dcf7365eea1955ab710abd1f","abstract_canon_sha256":"9f8e3652ecad5ff29ada07d8333fcaf4b6aef6481b86a2d3bfb47318165e0b8b"},"schema_version":"1.0"},"canonical_sha256":"2505dd720cc907a923ad738d43873e3743e1d3087b96753ad6ebbedcc96d0607","source":{"kind":"arxiv","id":"1703.09833","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.09833","created_at":"2026-05-18T00:41:53Z"},{"alias_kind":"arxiv_version","alias_value":"1703.09833v2","created_at":"2026-05-18T00:41:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.09833","created_at":"2026-05-18T00:41:53Z"},{"alias_kind":"pith_short_12","alias_value":"EUC524QMZED2","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EUC524QMZED2SI5N","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EUC524QM","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EUC524QMZED2SI5NOOGUHBZ6G5","target":"record","payload":{"canonical_record":{"source":{"id":"1703.09833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-28T22:47:04Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"7b6a8d0af763104bc7167abca06c2b5dbafc6636dcf7365eea1955ab710abd1f","abstract_canon_sha256":"9f8e3652ecad5ff29ada07d8333fcaf4b6aef6481b86a2d3bfb47318165e0b8b"},"schema_version":"1.0"},"canonical_sha256":"2505dd720cc907a923ad738d43873e3743e1d3087b96753ad6ebbedcc96d0607","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:53.039766Z","signature_b64":"0fNTxaC6e5IzfRh2hfmJ5L2teFQ4h17C9ElfVN86nYm63ka/q6uWlLfrKizmXEx0/CnF/w6ydi7yTZSZHU/VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2505dd720cc907a923ad738d43873e3743e1d3087b96753ad6ebbedcc96d0607","last_reissued_at":"2026-05-18T00:41:53.039276Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:53.039276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.09833","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":"2026-05-18T00:41:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t+YX+AEuwHat4ZhAztj7SIdCSlLnekrmLkW1y5QMpG87v1FEbX7OJQ4pjqWrkviDuwKx0o8yUbqFY6vb/kVpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:05:25.993888Z"},"content_sha256":"1bbe91172debf2ecbce840d0655c4af56bfb16a21fb3f7ba25cfc5db92b3fdfc","schema_version":"1.0","event_id":"sha256:1bbe91172debf2ecbce840d0655c4af56bfb16a21fb3f7ba25cfc5db92b3fdfc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EUC524QMZED2SI5NOOGUHBZ6G5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Theory II: Landscape of the Empirical Risk in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Qianli Liao, Tomaso Poggio","submitted_at":"2017-03-28T22:47:04Z","abstract_excerpt":"Previous theoretical work on deep learning and neural network optimization tend to focus on avoiding saddle points and local minima. However, the practical observation is that, at least in the case of the most successful Deep Convolutional Neural Networks (DCNNs), practitioners can always increase the network size to fit the training data (an extreme example would be [1]). The most successful DCNNs such as VGG and ResNets are best used with a degree of \"overparametrization\". In this work, we characterize with a mix of theory and experiments, the landscape of the empirical risk of overparametri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.09833","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":""},"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":"2026-05-18T00:41:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZDvfcaYpqbDPeNR2Jol0MHmUMowBHAxXljYDGmhZwN/1xNsTM2DlY9iGk33H4/uSenjhl4rBre4kTHUml0HDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:05:25.994595Z"},"content_sha256":"d15937afec39115f82067127695d64c33f266f1b0b40c9e51367b17b96e74ee5","schema_version":"1.0","event_id":"sha256:d15937afec39115f82067127695d64c33f266f1b0b40c9e51367b17b96e74ee5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EUC524QMZED2SI5NOOGUHBZ6G5/bundle.json","state_url":"https://pith.science/pith/EUC524QMZED2SI5NOOGUHBZ6G5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EUC524QMZED2SI5NOOGUHBZ6G5/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":"2026-06-01T02:05:25Z","links":{"resolver":"https://pith.science/pith/EUC524QMZED2SI5NOOGUHBZ6G5","bundle":"https://pith.science/pith/EUC524QMZED2SI5NOOGUHBZ6G5/bundle.json","state":"https://pith.science/pith/EUC524QMZED2SI5NOOGUHBZ6G5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EUC524QMZED2SI5NOOGUHBZ6G5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EUC524QMZED2SI5NOOGUHBZ6G5","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":"9f8e3652ecad5ff29ada07d8333fcaf4b6aef6481b86a2d3bfb47318165e0b8b","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-28T22:47:04Z","title_canon_sha256":"7b6a8d0af763104bc7167abca06c2b5dbafc6636dcf7365eea1955ab710abd1f"},"schema_version":"1.0","source":{"id":"1703.09833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.09833","created_at":"2026-05-18T00:41:53Z"},{"alias_kind":"arxiv_version","alias_value":"1703.09833v2","created_at":"2026-05-18T00:41:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.09833","created_at":"2026-05-18T00:41:53Z"},{"alias_kind":"pith_short_12","alias_value":"EUC524QMZED2","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EUC524QMZED2SI5N","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EUC524QM","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:d15937afec39115f82067127695d64c33f266f1b0b40c9e51367b17b96e74ee5","target":"graph","created_at":"2026-05-18T00:41:53Z","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"},"paper":{"abstract_excerpt":"Previous theoretical work on deep learning and neural network optimization tend to focus on avoiding saddle points and local minima. However, the practical observation is that, at least in the case of the most successful Deep Convolutional Neural Networks (DCNNs), practitioners can always increase the network size to fit the training data (an extreme example would be [1]). The most successful DCNNs such as VGG and ResNets are best used with a degree of \"overparametrization\". In this work, we characterize with a mix of theory and experiments, the landscape of the empirical risk of overparametri","authors_text":"Qianli Liao, Tomaso Poggio","cross_cats":["cs.CV","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-28T22:47:04Z","title":"Theory II: Landscape of the Empirical Risk in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.09833","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":"sha256:1bbe91172debf2ecbce840d0655c4af56bfb16a21fb3f7ba25cfc5db92b3fdfc","target":"record","created_at":"2026-05-18T00:41:53Z","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":"9f8e3652ecad5ff29ada07d8333fcaf4b6aef6481b86a2d3bfb47318165e0b8b","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-28T22:47:04Z","title_canon_sha256":"7b6a8d0af763104bc7167abca06c2b5dbafc6636dcf7365eea1955ab710abd1f"},"schema_version":"1.0","source":{"id":"1703.09833","kind":"arxiv","version":2}},"canonical_sha256":"2505dd720cc907a923ad738d43873e3743e1d3087b96753ad6ebbedcc96d0607","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2505dd720cc907a923ad738d43873e3743e1d3087b96753ad6ebbedcc96d0607","first_computed_at":"2026-05-18T00:41:53.039276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:53.039276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0fNTxaC6e5IzfRh2hfmJ5L2teFQ4h17C9ElfVN86nYm63ka/q6uWlLfrKizmXEx0/CnF/w6ydi7yTZSZHU/VAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:53.039766Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.09833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bbe91172debf2ecbce840d0655c4af56bfb16a21fb3f7ba25cfc5db92b3fdfc","sha256:d15937afec39115f82067127695d64c33f266f1b0b40c9e51367b17b96e74ee5"],"state_sha256":"48571f520600ee65a633e9b2a49837a2ef019acc5420e29f439743850809f516"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zvAqOM8+U3fP35THCvtO8S3V1Rug5YQhta/684fQgNwEqO+HwJG7p4EfTlSigI5TJvQvqHVk+oEDaunnlL7PDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T02:05:25.998266Z","bundle_sha256":"27c83ebbb77d83eec1dfd812bdc757e321f68ee6d03c4c82226e28722687870f"}}