{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3YACCKM2MKKMGCKZVQGK42L7GA","short_pith_number":"pith:3YACCKM2","canonical_record":{"source":{"id":"1710.10928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T13:24:28Z","cross_cats_sorted":["cs.AI","cs.CV","math.OC","stat.ML"],"title_canon_sha256":"e62b87a5eb7784092cef166c66abf71814e248a992c2351ae21483a450ff94f0","abstract_canon_sha256":"bfe0247ba2deec5894e1de9a3e5eef939fe103d2b684e1de937d54a57e681f7e"},"schema_version":"1.0"},"canonical_sha256":"de0021299a6294c30959ac0cae697f30392ca76cdef531f7768a1da0827456a1","source":{"kind":"arxiv","id":"1710.10928","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.10928","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"1710.10928v2","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10928","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"3YACCKM2MKKM","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3YACCKM2MKKMGCKZ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3YACCKM2","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3YACCKM2MKKMGCKZVQGK42L7GA","target":"record","payload":{"canonical_record":{"source":{"id":"1710.10928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T13:24:28Z","cross_cats_sorted":["cs.AI","cs.CV","math.OC","stat.ML"],"title_canon_sha256":"e62b87a5eb7784092cef166c66abf71814e248a992c2351ae21483a450ff94f0","abstract_canon_sha256":"bfe0247ba2deec5894e1de9a3e5eef939fe103d2b684e1de937d54a57e681f7e"},"schema_version":"1.0"},"canonical_sha256":"de0021299a6294c30959ac0cae697f30392ca76cdef531f7768a1da0827456a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.612455Z","signature_b64":"FwXjkx7bBMVQYFcXctcRAQ4exaLn4XLk7ZWz5gRq4H03IFSXAuShOQzzeTzuJp47nTQmOjOBVBljTtjl52o2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de0021299a6294c30959ac0cae697f30392ca76cdef531f7768a1da0827456a1","last_reissued_at":"2026-05-18T00:14:06.611974Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.611974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.10928","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":"2026-05-18T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6jnoGN/eh4AY8oO/aYsLBu9w8V0OaiM2ijrCMFbpt4w38ukVIOZn5oLyh+2BzPVpmagBWvr4ta06Q9JMH5aSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:11:22.891613Z"},"content_sha256":"b293e73fd0817d6e8846e6a5183c5b2b468f7957b0518c5fa3b3928af774a6b8","schema_version":"1.0","event_id":"sha256:b293e73fd0817d6e8846e6a5183c5b2b468f7957b0518c5fa3b3928af774a6b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3YACCKM2MKKMGCKZVQGK42L7GA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimization Landscape and Expressivity of Deep CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthias Hein, Quynh Nguyen","submitted_at":"2017-10-30T13:24:28Z","abstract_excerpt":"We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a \"wide\" layer which has more neurons than the number of training samples. This condition holds e.g. for the VGG network. Furthermore, we provide for such wide CNNs necessary and sufficient conditions for global minima with zero training error. For the case where the wide layer is followed by a fully connected layer we show that almost every critical point of the empirical loss is a gl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10928","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":"2026-05-18T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UF+BSqGY7NhL+US/fnUjfx5W8weg5RqO6Fjdr9NTCSX1p8g9N4HirD6xt5zwWCgs9CKvclKxyLsMGOPrECMFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:11:22.892362Z"},"content_sha256":"4ee606bfaa50040332a696d471b4db4856586579e5d3be688165f71c31d2cccb","schema_version":"1.0","event_id":"sha256:4ee606bfaa50040332a696d471b4db4856586579e5d3be688165f71c31d2cccb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YACCKM2MKKMGCKZVQGK42L7GA/bundle.json","state_url":"https://pith.science/pith/3YACCKM2MKKMGCKZVQGK42L7GA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YACCKM2MKKMGCKZVQGK42L7GA/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":"2026-06-06T11:11:22Z","links":{"resolver":"https://pith.science/pith/3YACCKM2MKKMGCKZVQGK42L7GA","bundle":"https://pith.science/pith/3YACCKM2MKKMGCKZVQGK42L7GA/bundle.json","state":"https://pith.science/pith/3YACCKM2MKKMGCKZVQGK42L7GA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YACCKM2MKKMGCKZVQGK42L7GA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3YACCKM2MKKMGCKZVQGK42L7GA","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":"bfe0247ba2deec5894e1de9a3e5eef939fe103d2b684e1de937d54a57e681f7e","cross_cats_sorted":["cs.AI","cs.CV","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T13:24:28Z","title_canon_sha256":"e62b87a5eb7784092cef166c66abf71814e248a992c2351ae21483a450ff94f0"},"schema_version":"1.0","source":{"id":"1710.10928","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.10928","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"1710.10928v2","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10928","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"3YACCKM2MKKM","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3YACCKM2MKKMGCKZ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3YACCKM2","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:4ee606bfaa50040332a696d471b4db4856586579e5d3be688165f71c31d2cccb","target":"graph","created_at":"2026-05-18T00:14:06Z","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":"We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a \"wide\" layer which has more neurons than the number of training samples. This condition holds e.g. for the VGG network. Furthermore, we provide for such wide CNNs necessary and sufficient conditions for global minima with zero training error. For the case where the wide layer is followed by a fully connected layer we show that almost every critical point of the empirical loss is a gl","authors_text":"Matthias Hein, Quynh Nguyen","cross_cats":["cs.AI","cs.CV","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T13:24:28Z","title":"Optimization Landscape and Expressivity of Deep CNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10928","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:b293e73fd0817d6e8846e6a5183c5b2b468f7957b0518c5fa3b3928af774a6b8","target":"record","created_at":"2026-05-18T00:14:06Z","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":"bfe0247ba2deec5894e1de9a3e5eef939fe103d2b684e1de937d54a57e681f7e","cross_cats_sorted":["cs.AI","cs.CV","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T13:24:28Z","title_canon_sha256":"e62b87a5eb7784092cef166c66abf71814e248a992c2351ae21483a450ff94f0"},"schema_version":"1.0","source":{"id":"1710.10928","kind":"arxiv","version":2}},"canonical_sha256":"de0021299a6294c30959ac0cae697f30392ca76cdef531f7768a1da0827456a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de0021299a6294c30959ac0cae697f30392ca76cdef531f7768a1da0827456a1","first_computed_at":"2026-05-18T00:14:06.611974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:06.611974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FwXjkx7bBMVQYFcXctcRAQ4exaLn4XLk7ZWz5gRq4H03IFSXAuShOQzzeTzuJp47nTQmOjOBVBljTtjl52o2Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:06.612455Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.10928","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b293e73fd0817d6e8846e6a5183c5b2b468f7957b0518c5fa3b3928af774a6b8","sha256:4ee606bfaa50040332a696d471b4db4856586579e5d3be688165f71c31d2cccb"],"state_sha256":"31c1ee9305793dc1ffeb9a2cb43f8798f7eac72c1a760ed6a477e842a6e87096"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b2IKoZ49REoxmV/SoQEHsIPa1fFvOv619cdKsUAlpuJHTaCrrn+KLWs4ucd2NTSuRVsf2GWHuhG6Xe5/u6VMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T11:11:22.896366Z","bundle_sha256":"47b4fc05500d20f6019091b5dc0c4d2ffb91802a16f6719025fc06a584f579d5"}}