{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WW5FNND644KXUJ7ST4DUB3VMKW","short_pith_number":"pith:WW5FNND6","canonical_record":{"source":{"id":"1711.04313","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-12T15:42:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ff6f4ed6b66d65f4515430833a1fcd9858ab1388257e3a8b92ba3b26ef64e28","abstract_canon_sha256":"f2d57d7cda1e2280241b1a7dc34fb9bb6c8184faf50d3bc80e93fceaf27cd5e8"},"schema_version":"1.0"},"canonical_sha256":"b5ba56b47ee7157a27f29f0740eeac55a5e70d47285434a508e2bfb1f27515fb","source":{"kind":"arxiv","id":"1711.04313","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04313","created_at":"2026-05-18T00:30:39Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04313v1","created_at":"2026-05-18T00:30:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04313","created_at":"2026-05-18T00:30:39Z"},{"alias_kind":"pith_short_12","alias_value":"WW5FNND644KX","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WW5FNND644KXUJ7S","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WW5FNND6","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WW5FNND644KXUJ7ST4DUB3VMKW","target":"record","payload":{"canonical_record":{"source":{"id":"1711.04313","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-12T15:42:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ff6f4ed6b66d65f4515430833a1fcd9858ab1388257e3a8b92ba3b26ef64e28","abstract_canon_sha256":"f2d57d7cda1e2280241b1a7dc34fb9bb6c8184faf50d3bc80e93fceaf27cd5e8"},"schema_version":"1.0"},"canonical_sha256":"b5ba56b47ee7157a27f29f0740eeac55a5e70d47285434a508e2bfb1f27515fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:39.441519Z","signature_b64":"GztWv1E6LylxNMhvlpVZLoEyZgnkb2zqDr9cDoNrM2ZnahclYGO6awqbImWp8JO83liY6LqnNsvbwevsvSAyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5ba56b47ee7157a27f29f0740eeac55a5e70d47285434a508e2bfb1f27515fb","last_reissued_at":"2026-05-18T00:30:39.440770Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:39.440770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.04313","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":"2026-05-18T00:30:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdEKnIcdhJwKrBJyu8hdoSHE37s+sR5c6gDkWGDn3HztRESsrCtYRJ5cExpKcxl3BUEJjEPvBy5ldgEWVPJ4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:29:57.763602Z"},"content_sha256":"1cd301abc2171c1622f12cdeadf4f3d48a21c630ab16922add5d977881b25b1a","schema_version":"1.0","event_id":"sha256:1cd301abc2171c1622f12cdeadf4f3d48a21c630ab16922add5d977881b25b1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WW5FNND644KXUJ7ST4DUB3VMKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning via New Deep Network Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Herve G. Glotin, Randall Balestriero, Richard G. Baraniuk, Vincent Roger","submitted_at":"2017-11-12T15:42:24Z","abstract_excerpt":"We exploit a recently derived inversion scheme for arbitrary deep neural networks to develop a new semi-supervised learning framework that applies to a wide range of systems and problems. The approach outperforms current state-of-the-art methods on MNIST reaching $99.14\\%$ of test set accuracy while using $5$ labeled examples per class. Experiments with one-dimensional signals highlight the generality of the method. Importantly, our approach is simple, efficient, and requires no change in the deep network architecture."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04313","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":"2026-05-18T00:30:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ineLQx0c1tbJwfBOuM7quvrMy2dB6MUlqbbJCC4DA0sqmWVGaD0+xM0JTOBEIeKztSlC7Tyg3QaXo2b8UdDeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:29:57.764444Z"},"content_sha256":"2e511a8142bf9a51ed160704c67c0bdcf10d811bc0128c065a234233bdd06c36","schema_version":"1.0","event_id":"sha256:2e511a8142bf9a51ed160704c67c0bdcf10d811bc0128c065a234233bdd06c36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/bundle.json","state_url":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WW5FNND644KXUJ7ST4DUB3VMKW/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":"2026-05-31T14:29:57Z","links":{"resolver":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW","bundle":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/bundle.json","state":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WW5FNND644KXUJ7ST4DUB3VMKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WW5FNND644KXUJ7ST4DUB3VMKW","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":"f2d57d7cda1e2280241b1a7dc34fb9bb6c8184faf50d3bc80e93fceaf27cd5e8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-12T15:42:24Z","title_canon_sha256":"4ff6f4ed6b66d65f4515430833a1fcd9858ab1388257e3a8b92ba3b26ef64e28"},"schema_version":"1.0","source":{"id":"1711.04313","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04313","created_at":"2026-05-18T00:30:39Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04313v1","created_at":"2026-05-18T00:30:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04313","created_at":"2026-05-18T00:30:39Z"},{"alias_kind":"pith_short_12","alias_value":"WW5FNND644KX","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WW5FNND644KXUJ7S","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WW5FNND6","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:2e511a8142bf9a51ed160704c67c0bdcf10d811bc0128c065a234233bdd06c36","target":"graph","created_at":"2026-05-18T00:30:39Z","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 exploit a recently derived inversion scheme for arbitrary deep neural networks to develop a new semi-supervised learning framework that applies to a wide range of systems and problems. The approach outperforms current state-of-the-art methods on MNIST reaching $99.14\\%$ of test set accuracy while using $5$ labeled examples per class. Experiments with one-dimensional signals highlight the generality of the method. Importantly, our approach is simple, efficient, and requires no change in the deep network architecture.","authors_text":"Herve G. Glotin, Randall Balestriero, Richard G. Baraniuk, Vincent Roger","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-12T15:42:24Z","title":"Semi-Supervised Learning via New Deep Network Inversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04313","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":"sha256:1cd301abc2171c1622f12cdeadf4f3d48a21c630ab16922add5d977881b25b1a","target":"record","created_at":"2026-05-18T00:30:39Z","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":"f2d57d7cda1e2280241b1a7dc34fb9bb6c8184faf50d3bc80e93fceaf27cd5e8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-12T15:42:24Z","title_canon_sha256":"4ff6f4ed6b66d65f4515430833a1fcd9858ab1388257e3a8b92ba3b26ef64e28"},"schema_version":"1.0","source":{"id":"1711.04313","kind":"arxiv","version":1}},"canonical_sha256":"b5ba56b47ee7157a27f29f0740eeac55a5e70d47285434a508e2bfb1f27515fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5ba56b47ee7157a27f29f0740eeac55a5e70d47285434a508e2bfb1f27515fb","first_computed_at":"2026-05-18T00:30:39.440770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:39.440770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GztWv1E6LylxNMhvlpVZLoEyZgnkb2zqDr9cDoNrM2ZnahclYGO6awqbImWp8JO83liY6LqnNsvbwevsvSAyBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:39.441519Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.04313","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cd301abc2171c1622f12cdeadf4f3d48a21c630ab16922add5d977881b25b1a","sha256:2e511a8142bf9a51ed160704c67c0bdcf10d811bc0128c065a234233bdd06c36"],"state_sha256":"aa765fab9cdcbc6ecbb4dc89c537aa41fbc1f242e371e2ff15d28e5de5c67e43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GDXOnbDY0dtFGUaWRSGgOpt87HOm5u3B3UHRV46TbH5GCgw/hV9XEiOlCRu2qk75NlGt1j8rPzT4RmHlMFCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T14:29:57.768443Z","bundle_sha256":"26b7488ca082c1cb27ab9c58d29db70d0627fd9d961b2e25f4765cedf5e7a67d"}}