{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BELOSC5ZYRPFMARUVCPGD5FL3O","short_pith_number":"pith:BELOSC5Z","canonical_record":{"source":{"id":"1606.05579","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T16:19:46Z","cross_cats_sorted":["cs.LG","q-bio.NC"],"title_canon_sha256":"5ac11fd6a9d172f59e26a1eeb1d1223223be4ca750231485572019d431acb5c3","abstract_canon_sha256":"7fdfb11abfcbc09bce29e0dc2135cfb47d97a391faab72d25421240f783077b6"},"schema_version":"1.0"},"canonical_sha256":"0916e90bb9c45e560234a89e61f4abdba6a2379748ae86d6bd991db98e6bc4e0","source":{"kind":"arxiv","id":"1606.05579","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05579","created_at":"2026-05-18T01:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05579v3","created_at":"2026-05-18T01:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05579","created_at":"2026-05-18T01:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"BELOSC5ZYRPF","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BELOSC5ZYRPFMARU","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BELOSC5Z","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BELOSC5ZYRPFMARUVCPGD5FL3O","target":"record","payload":{"canonical_record":{"source":{"id":"1606.05579","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T16:19:46Z","cross_cats_sorted":["cs.LG","q-bio.NC"],"title_canon_sha256":"5ac11fd6a9d172f59e26a1eeb1d1223223be4ca750231485572019d431acb5c3","abstract_canon_sha256":"7fdfb11abfcbc09bce29e0dc2135cfb47d97a391faab72d25421240f783077b6"},"schema_version":"1.0"},"canonical_sha256":"0916e90bb9c45e560234a89e61f4abdba6a2379748ae86d6bd991db98e6bc4e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:18.581289Z","signature_b64":"Yie9t0o7ptldIc7FgNsYWzqb+xN49EEtSAli1FIaFhsXLGtV6gV2WfJtYXDHcKO0I+J6MrZ4itVlpQ+B/2c6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0916e90bb9c45e560234a89e61f4abdba6a2379748ae86d6bd991db98e6bc4e0","last_reissued_at":"2026-05-18T01:04:18.580890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:18.580890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.05579","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"695naAguExGRMoQ8cmLIUgRmwr9yvhOwZj34eDuX6LlYRVN+I2UvbvHZZokJHwr2XIJdUrICBKgVNXkbg1WIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:22:42.068251Z"},"content_sha256":"dd6d78c06d1de9c8a809f0c3e41ab007fef67d3da3f60e430ed65efa7d951e12","schema_version":"1.0","event_id":"sha256:dd6d78c06d1de9c8a809f0c3e41ab007fef67d3da3f60e430ed65efa7d951e12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BELOSC5ZYRPFMARUVCPGD5FL3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Early Visual Concept Learning with Unsupervised Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Alexander Lerchner, Arka Pal, Benigno Uria, Charles Blundell, Irina Higgins, Loic Matthey, Shakir Mohamed, Xavier Glorot","submitted_at":"2016-06-17T16:19:46Z","abstract_excerpt":"Automated discovery of early visual concepts from raw image data is a major open challenge in AI research. Addressing this problem, we propose an unsupervised approach for learning disentangled representations of the underlying factors of variation. We draw inspiration from neuroscience, and show how this can be achieved in an unsupervised generative model by applying the same learning pressures as have been suggested to act in the ventral visual stream in the brain. By enforcing redundancy reduction, encouraging statistical independence, and exposure to data with transform continuities analog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05579","kind":"arxiv","version":3},"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":"2026-05-18T01:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IH+v3aMIWgjobqcvRP6eALSeCYd/4+4rIgqig0sNiKGy6p8enEY2+zOJb/T0xYnBMp+wFn/pPHg6fCmlC7rFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:22:42.068685Z"},"content_sha256":"a2cc9b3b5096ee9a43946a0a11b4b8dd4e019218083be2328f7e0ed61bed96ea","schema_version":"1.0","event_id":"sha256:a2cc9b3b5096ee9a43946a0a11b4b8dd4e019218083be2328f7e0ed61bed96ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BELOSC5ZYRPFMARUVCPGD5FL3O/bundle.json","state_url":"https://pith.science/pith/BELOSC5ZYRPFMARUVCPGD5FL3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BELOSC5ZYRPFMARUVCPGD5FL3O/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":"2026-05-31T19:22:42Z","links":{"resolver":"https://pith.science/pith/BELOSC5ZYRPFMARUVCPGD5FL3O","bundle":"https://pith.science/pith/BELOSC5ZYRPFMARUVCPGD5FL3O/bundle.json","state":"https://pith.science/pith/BELOSC5ZYRPFMARUVCPGD5FL3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BELOSC5ZYRPFMARUVCPGD5FL3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BELOSC5ZYRPFMARUVCPGD5FL3O","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":"7fdfb11abfcbc09bce29e0dc2135cfb47d97a391faab72d25421240f783077b6","cross_cats_sorted":["cs.LG","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T16:19:46Z","title_canon_sha256":"5ac11fd6a9d172f59e26a1eeb1d1223223be4ca750231485572019d431acb5c3"},"schema_version":"1.0","source":{"id":"1606.05579","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05579","created_at":"2026-05-18T01:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05579v3","created_at":"2026-05-18T01:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05579","created_at":"2026-05-18T01:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"BELOSC5ZYRPF","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BELOSC5ZYRPFMARU","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BELOSC5Z","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:a2cc9b3b5096ee9a43946a0a11b4b8dd4e019218083be2328f7e0ed61bed96ea","target":"graph","created_at":"2026-05-18T01:04:18Z","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":"Automated discovery of early visual concepts from raw image data is a major open challenge in AI research. Addressing this problem, we propose an unsupervised approach for learning disentangled representations of the underlying factors of variation. We draw inspiration from neuroscience, and show how this can be achieved in an unsupervised generative model by applying the same learning pressures as have been suggested to act in the ventral visual stream in the brain. By enforcing redundancy reduction, encouraging statistical independence, and exposure to data with transform continuities analog","authors_text":"Alexander Lerchner, Arka Pal, Benigno Uria, Charles Blundell, Irina Higgins, Loic Matthey, Shakir Mohamed, Xavier Glorot","cross_cats":["cs.LG","q-bio.NC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T16:19:46Z","title":"Early Visual Concept Learning with Unsupervised Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05579","kind":"arxiv","version":3},"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:dd6d78c06d1de9c8a809f0c3e41ab007fef67d3da3f60e430ed65efa7d951e12","target":"record","created_at":"2026-05-18T01:04:18Z","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":"7fdfb11abfcbc09bce29e0dc2135cfb47d97a391faab72d25421240f783077b6","cross_cats_sorted":["cs.LG","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T16:19:46Z","title_canon_sha256":"5ac11fd6a9d172f59e26a1eeb1d1223223be4ca750231485572019d431acb5c3"},"schema_version":"1.0","source":{"id":"1606.05579","kind":"arxiv","version":3}},"canonical_sha256":"0916e90bb9c45e560234a89e61f4abdba6a2379748ae86d6bd991db98e6bc4e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0916e90bb9c45e560234a89e61f4abdba6a2379748ae86d6bd991db98e6bc4e0","first_computed_at":"2026-05-18T01:04:18.580890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:18.580890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yie9t0o7ptldIc7FgNsYWzqb+xN49EEtSAli1FIaFhsXLGtV6gV2WfJtYXDHcKO0I+J6MrZ4itVlpQ+B/2c6Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:18.581289Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.05579","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd6d78c06d1de9c8a809f0c3e41ab007fef67d3da3f60e430ed65efa7d951e12","sha256:a2cc9b3b5096ee9a43946a0a11b4b8dd4e019218083be2328f7e0ed61bed96ea"],"state_sha256":"9f1f138a2f0f7f3d895f2a9b6122f54edc8a1225794c2651b086d870af211cf6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"htHmda77q6/vCzt1Tsmggpw7Y3ft/tEvA/fSjuzakEAkozB3xo+5qtHwWMgWYzf53BF4A5xDkcsBdsomwBBIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:22:42.071329Z","bundle_sha256":"ca46788b3642baf46c1cc2b87daaa05064a871fb0c9ff6479ac435e612c53494"}}