{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WNWHECYJ4MPOTTNYU4R52J3GT5","short_pith_number":"pith:WNWHECYJ","canonical_record":{"source":{"id":"1608.03714","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2016-08-12T08:35:22Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"title_canon_sha256":"ca512c25b137af529dc6bd7eea6f4bc354ce9e422c1ad39ec637969c6cf50597","abstract_canon_sha256":"27c222c1e0da81e0b90b3ad7511ff601c72826472449e410220d9ee29ea7e671"},"schema_version":"1.0"},"canonical_sha256":"b36c720b09e31ee9cdb8a723dd27669f61f99f1d2d9febc364355b63036e5c9f","source":{"kind":"arxiv","id":"1608.03714","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.03714","created_at":"2026-05-18T00:54:10Z"},{"alias_kind":"arxiv_version","alias_value":"1608.03714v2","created_at":"2026-05-18T00:54:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.03714","created_at":"2026-05-18T00:54:10Z"},{"alias_kind":"pith_short_12","alias_value":"WNWHECYJ4MPO","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WNWHECYJ4MPOTTNY","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WNWHECYJ","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WNWHECYJ4MPOTTNYU4R52J3GT5","target":"record","payload":{"canonical_record":{"source":{"id":"1608.03714","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2016-08-12T08:35:22Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"title_canon_sha256":"ca512c25b137af529dc6bd7eea6f4bc354ce9e422c1ad39ec637969c6cf50597","abstract_canon_sha256":"27c222c1e0da81e0b90b3ad7511ff601c72826472449e410220d9ee29ea7e671"},"schema_version":"1.0"},"canonical_sha256":"b36c720b09e31ee9cdb8a723dd27669f61f99f1d2d9febc364355b63036e5c9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:10.601532Z","signature_b64":"+X1DBiOaxuyZJ+2JRgjq0HMfVvOs7DhA8J2o30kGEkoLDMdcsUBaAOOdHxT3JyWJ7Yy72WJaELlMb5+tgUO1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b36c720b09e31ee9cdb8a723dd27669f61f99f1d2d9febc364355b63036e5c9f","last_reissued_at":"2026-05-18T00:54:10.601117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:10.601117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.03714","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":"2026-05-18T00:54:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"54DE/0EozOebhF/qW9rftMgYA2OCdEME8tVIKqszPZmY2Bo1rU6xXvOu+/VsFMvWFF3bvUumO0J6fiJrGzAkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T08:18:40.868597Z"},"content_sha256":"4dbad75ce2902965de35d8d32e0eaef753a3ac98d4095698d87f72b255c095fa","schema_version":"1.0","event_id":"sha256:4dbad75ce2902965de35d8d32e0eaef753a3ac98d4095698d87f72b255c095fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WNWHECYJ4MPOTTNYU4R52J3GT5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised feature learning from finite data by message passing: discontinuous versus continuous phase transition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"primary_cat":"cond-mat.dis-nn","authors_text":"Haiping Huang, Taro Toyoizumi","submitted_at":"2016-08-12T08:35:22Z","abstract_excerpt":"Unsupervised neural network learning extracts hidden features from unlabeled training data. This is used as a pretraining step for further supervised learning in deep networks. Hence, understanding unsupervised learning is of fundamental importance. Here, we study the unsupervised learning from a finite number of data, based on the restricted Boltzmann machine learning. Our study inspires an efficient message passing algorithm to infer the hidden feature, and estimate the entropy of candidate features consistent with the data. Our analysis reveals that the learning requires only a few data if "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.03714","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":"2026-05-18T00:54:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHf2TGni9omc+6jTaKNRCt2iTdE0d5EyZCeuY7xL3UFmsfi3YhAFNbQT7FdqPKebetDPvWImyPE8hPSsFL/LAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T08:18:40.868949Z"},"content_sha256":"39a34ee8b1886e438aebec0e5eb48de394cce7d1a5dd1d8c43a058d3d3bc6fe8","schema_version":"1.0","event_id":"sha256:39a34ee8b1886e438aebec0e5eb48de394cce7d1a5dd1d8c43a058d3d3bc6fe8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WNWHECYJ4MPOTTNYU4R52J3GT5/bundle.json","state_url":"https://pith.science/pith/WNWHECYJ4MPOTTNYU4R52J3GT5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WNWHECYJ4MPOTTNYU4R52J3GT5/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":"2026-06-26T08:18:40Z","links":{"resolver":"https://pith.science/pith/WNWHECYJ4MPOTTNYU4R52J3GT5","bundle":"https://pith.science/pith/WNWHECYJ4MPOTTNYU4R52J3GT5/bundle.json","state":"https://pith.science/pith/WNWHECYJ4MPOTTNYU4R52J3GT5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WNWHECYJ4MPOTTNYU4R52J3GT5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WNWHECYJ4MPOTTNYU4R52J3GT5","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":"27c222c1e0da81e0b90b3ad7511ff601c72826472449e410220d9ee29ea7e671","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2016-08-12T08:35:22Z","title_canon_sha256":"ca512c25b137af529dc6bd7eea6f4bc354ce9e422c1ad39ec637969c6cf50597"},"schema_version":"1.0","source":{"id":"1608.03714","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.03714","created_at":"2026-05-18T00:54:10Z"},{"alias_kind":"arxiv_version","alias_value":"1608.03714v2","created_at":"2026-05-18T00:54:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.03714","created_at":"2026-05-18T00:54:10Z"},{"alias_kind":"pith_short_12","alias_value":"WNWHECYJ4MPO","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WNWHECYJ4MPOTTNY","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WNWHECYJ","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:39a34ee8b1886e438aebec0e5eb48de394cce7d1a5dd1d8c43a058d3d3bc6fe8","target":"graph","created_at":"2026-05-18T00:54:10Z","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":"Unsupervised neural network learning extracts hidden features from unlabeled training data. This is used as a pretraining step for further supervised learning in deep networks. Hence, understanding unsupervised learning is of fundamental importance. Here, we study the unsupervised learning from a finite number of data, based on the restricted Boltzmann machine learning. Our study inspires an efficient message passing algorithm to infer the hidden feature, and estimate the entropy of candidate features consistent with the data. Our analysis reveals that the learning requires only a few data if ","authors_text":"Haiping Huang, Taro Toyoizumi","cross_cats":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2016-08-12T08:35:22Z","title":"Unsupervised feature learning from finite data by message passing: discontinuous versus continuous phase transition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.03714","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":"sha256:4dbad75ce2902965de35d8d32e0eaef753a3ac98d4095698d87f72b255c095fa","target":"record","created_at":"2026-05-18T00:54:10Z","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":"27c222c1e0da81e0b90b3ad7511ff601c72826472449e410220d9ee29ea7e671","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2016-08-12T08:35:22Z","title_canon_sha256":"ca512c25b137af529dc6bd7eea6f4bc354ce9e422c1ad39ec637969c6cf50597"},"schema_version":"1.0","source":{"id":"1608.03714","kind":"arxiv","version":2}},"canonical_sha256":"b36c720b09e31ee9cdb8a723dd27669f61f99f1d2d9febc364355b63036e5c9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b36c720b09e31ee9cdb8a723dd27669f61f99f1d2d9febc364355b63036e5c9f","first_computed_at":"2026-05-18T00:54:10.601117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:54:10.601117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+X1DBiOaxuyZJ+2JRgjq0HMfVvOs7DhA8J2o30kGEkoLDMdcsUBaAOOdHxT3JyWJ7Yy72WJaELlMb5+tgUO1CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:54:10.601532Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.03714","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dbad75ce2902965de35d8d32e0eaef753a3ac98d4095698d87f72b255c095fa","sha256:39a34ee8b1886e438aebec0e5eb48de394cce7d1a5dd1d8c43a058d3d3bc6fe8"],"state_sha256":"5d3bebbdc41f89c2d37f69ae913269657fc48176e775d62b07671ade78ea09c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84Wd7XDnRtF27D5rq2T0FNyD3qSGrQP3XJ3FCahi+3rchbsmEV68xGLIxIIEpSrrO0pXUKe/cQp20hnzPb9GDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T08:18:40.871170Z","bundle_sha256":"352d79cec73225ccd6eefc9eab5f2e37946e33a08beb9a2da1940e19738cc8c6"}}