{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JCODI7VMPI3RL2PE4UXBUBE7OR","short_pith_number":"pith:JCODI7VM","canonical_record":{"source":{"id":"1907.00485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T22:27:13Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"3ef4035485472f51a7f49be4d011b4d95d37088c26525f0eac89e72213bd2f63","abstract_canon_sha256":"51957d9e54ea816dbc57de078b6ce2b384f570bfb8e9d2e973b119c1a7f16abd"},"schema_version":"1.0"},"canonical_sha256":"489c347eac7a3715e9e4e52e1a049f746db7fb05c6c02c18181a892c751058ff","source":{"kind":"arxiv","id":"1907.00485","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00485","created_at":"2026-05-17T23:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00485v1","created_at":"2026-05-17T23:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00485","created_at":"2026-05-17T23:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"JCODI7VMPI3R","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"JCODI7VMPI3RL2PE","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"JCODI7VM","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JCODI7VMPI3RL2PE4UXBUBE7OR","target":"record","payload":{"canonical_record":{"source":{"id":"1907.00485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T22:27:13Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"3ef4035485472f51a7f49be4d011b4d95d37088c26525f0eac89e72213bd2f63","abstract_canon_sha256":"51957d9e54ea816dbc57de078b6ce2b384f570bfb8e9d2e973b119c1a7f16abd"},"schema_version":"1.0"},"canonical_sha256":"489c347eac7a3715e9e4e52e1a049f746db7fb05c6c02c18181a892c751058ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:51.484403Z","signature_b64":"xMKX3eKBmyLPU5baz8WukX0IgCtmz9WqakNkBXBlWcYuX4uwv5oiNoi1IoOQKQId7rMDbTm5bAIJsAgC6GiuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"489c347eac7a3715e9e4e52e1a049f746db7fb05c6c02c18181a892c751058ff","last_reissued_at":"2026-05-17T23:41:51.483685Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:51.483685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.00485","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":"2026-05-17T23:41:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C1+muiRCiHXQ69jPVg3X140DVqpoJRU6DJ53gkGS6d7G2XI0X3KyCXLeTqfNRh/vcwEXxAUW1F/tALeoommFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:04:44.334797Z"},"content_sha256":"b778c64efdf6dad07bcf59234f8521c766923370874bc0d7cc8f616a31b077c9","schema_version":"1.0","event_id":"sha256:b778c64efdf6dad07bcf59234f8521c766923370874bc0d7cc8f616a31b077c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JCODI7VMPI3RL2PE4UXBUBE7OR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Massimo Fornasier, Michael Rauchensteiner, Timo Klock","submitted_at":"2019-06-30T22:27:13Z","abstract_excerpt":"We address the structure identification and the uniform approximation of two fully nonlinear layer neural networks of the type $f(x)=1^T h(B^T g(A^T x))$ on $\\mathbb R^d$ from a small number of query samples. We approach the problem by sampling actively finite difference approximations to Hessians of the network. Gathering several approximate Hessians allows reliably to approximate the matrix subspace $\\mathcal W$ spanned by symmetric tensors $a_1 \\otimes a_1 ,\\dots,a_{m_0}\\otimes a_{m_0}$ formed by weights of the first layer together with the entangled symmetric tensors $v_1 \\otimes v_1 ,\\dot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00485","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8JS2y00dn1lQnlK8p3yEoBxNIgDXT4qA9ylm4gNJKkiRfhPwJGNa8D0swSM+wYh0mLnftTelwyfFsarwqmOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:04:44.335448Z"},"content_sha256":"b449979c4fe5c2afc3fff26bd32dbd3048e16ac6f19c51847d651612dfb98ed8","schema_version":"1.0","event_id":"sha256:b449979c4fe5c2afc3fff26bd32dbd3048e16ac6f19c51847d651612dfb98ed8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JCODI7VMPI3RL2PE4UXBUBE7OR/bundle.json","state_url":"https://pith.science/pith/JCODI7VMPI3RL2PE4UXBUBE7OR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JCODI7VMPI3RL2PE4UXBUBE7OR/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":"2026-05-26T07:04:44Z","links":{"resolver":"https://pith.science/pith/JCODI7VMPI3RL2PE4UXBUBE7OR","bundle":"https://pith.science/pith/JCODI7VMPI3RL2PE4UXBUBE7OR/bundle.json","state":"https://pith.science/pith/JCODI7VMPI3RL2PE4UXBUBE7OR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JCODI7VMPI3RL2PE4UXBUBE7OR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JCODI7VMPI3RL2PE4UXBUBE7OR","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":"51957d9e54ea816dbc57de078b6ce2b384f570bfb8e9d2e973b119c1a7f16abd","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T22:27:13Z","title_canon_sha256":"3ef4035485472f51a7f49be4d011b4d95d37088c26525f0eac89e72213bd2f63"},"schema_version":"1.0","source":{"id":"1907.00485","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00485","created_at":"2026-05-17T23:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00485v1","created_at":"2026-05-17T23:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00485","created_at":"2026-05-17T23:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"JCODI7VMPI3R","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"JCODI7VMPI3RL2PE","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"JCODI7VM","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:b449979c4fe5c2afc3fff26bd32dbd3048e16ac6f19c51847d651612dfb98ed8","target":"graph","created_at":"2026-05-17T23:41:51Z","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 address the structure identification and the uniform approximation of two fully nonlinear layer neural networks of the type $f(x)=1^T h(B^T g(A^T x))$ on $\\mathbb R^d$ from a small number of query samples. We approach the problem by sampling actively finite difference approximations to Hessians of the network. Gathering several approximate Hessians allows reliably to approximate the matrix subspace $\\mathcal W$ spanned by symmetric tensors $a_1 \\otimes a_1 ,\\dots,a_{m_0}\\otimes a_{m_0}$ formed by weights of the first layer together with the entangled symmetric tensors $v_1 \\otimes v_1 ,\\dot","authors_text":"Massimo Fornasier, Michael Rauchensteiner, Timo Klock","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T22:27:13Z","title":"Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00485","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:b778c64efdf6dad07bcf59234f8521c766923370874bc0d7cc8f616a31b077c9","target":"record","created_at":"2026-05-17T23:41:51Z","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":"51957d9e54ea816dbc57de078b6ce2b384f570bfb8e9d2e973b119c1a7f16abd","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T22:27:13Z","title_canon_sha256":"3ef4035485472f51a7f49be4d011b4d95d37088c26525f0eac89e72213bd2f63"},"schema_version":"1.0","source":{"id":"1907.00485","kind":"arxiv","version":1}},"canonical_sha256":"489c347eac7a3715e9e4e52e1a049f746db7fb05c6c02c18181a892c751058ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"489c347eac7a3715e9e4e52e1a049f746db7fb05c6c02c18181a892c751058ff","first_computed_at":"2026-05-17T23:41:51.483685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:51.483685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xMKX3eKBmyLPU5baz8WukX0IgCtmz9WqakNkBXBlWcYuX4uwv5oiNoi1IoOQKQId7rMDbTm5bAIJsAgC6GiuAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:51.484403Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.00485","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b778c64efdf6dad07bcf59234f8521c766923370874bc0d7cc8f616a31b077c9","sha256:b449979c4fe5c2afc3fff26bd32dbd3048e16ac6f19c51847d651612dfb98ed8"],"state_sha256":"5837cc9f6e12d40eac664aa8c9be0d965093ad8a440a835e436dc1aa248e2aab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pm/hlKfi6glDGvI+UyGy5emWQhF5M9tBXww4hQyORaSgny8MOfTy07yhxjGx10N5Q/k9M/jjCRVnzBh/6IJlCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:04:44.339294Z","bundle_sha256":"7077f1e503b1783baead2400a565f1a74b2d6636b74245c04a31a58a629d2aec"}}