{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7WDQ2LMI2RDD3IBWTDPHVFMLSB","short_pith_number":"pith:7WDQ2LMI","canonical_record":{"source":{"id":"2002.07766","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-18T17:58:07Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b7b9a39da9fc0c6064376f7e1e75b32315a7e2e4b735bc79456eedd7ba0a0499","abstract_canon_sha256":"136b459103365d5e7b7920c99124a49048f7700829510633be4a7b690086fb3d"},"schema_version":"1.0"},"canonical_sha256":"fd870d2d88d4463da03698de7a958b905722127bcbd13e69916d8ee486a33e0e","source":{"kind":"arxiv","id":"2002.07766","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.07766","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"2002.07766v5","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07766","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"7WDQ2LMI2RDD","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"pith_short_16","alias_value":"7WDQ2LMI2RDD3IBW","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"pith_short_8","alias_value":"7WDQ2LMI","created_at":"2026-07-05T02:10:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7WDQ2LMI2RDD3IBWTDPHVFMLSB","target":"record","payload":{"canonical_record":{"source":{"id":"2002.07766","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-18T17:58:07Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b7b9a39da9fc0c6064376f7e1e75b32315a7e2e4b735bc79456eedd7ba0a0499","abstract_canon_sha256":"136b459103365d5e7b7920c99124a49048f7700829510633be4a7b690086fb3d"},"schema_version":"1.0"},"canonical_sha256":"fd870d2d88d4463da03698de7a958b905722127bcbd13e69916d8ee486a33e0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:37.764624Z","signature_b64":"Uv/Uc09FUz4j5OOpFewaLr0gNBHvDG1SDTdMYEoqvj3XfHhooE9wmNFGfkS7c2geRI3fdiXUelV+IcB3yk54Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd870d2d88d4463da03698de7a958b905722127bcbd13e69916d8ee486a33e0e","last_reissued_at":"2026-07-05T02:10:37.764157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:37.764157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.07766","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:10:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vN1PV1Z8KrcCIsgbq7t6cD/tmB7/ANWsHcy9ikN6P106x3M21l87mqsjcrDzAMWQRR4XOEakmkmtFhb9aMt3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:39:16.299602Z"},"content_sha256":"40a92b77a67cf6934c20c95bc2f057a030371e3678ce52b6da671ac39448f610","schema_version":"1.0","event_id":"sha256:40a92b77a67cf6934c20c95bc2f057a030371e3678ce52b6da671ac39448f610"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7WDQ2LMI2RDD3IBWTDPHVFMLSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Bijective Feature Maps for Linear ICA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Camuto, Brooks Paige, Chris Holmes, Matthew Willetts, Stephen Roberts","submitted_at":"2020-02-18T17:58:07Z","abstract_excerpt":"Separating high-dimensional data like images into independent latent factors, i.e independent component analysis (ICA), remains an open research problem. As we show, existing probabilistic deep generative models (DGMs), which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. Given the complexities of jointly training such a hybrid model, we introduce novel theory that constrains linear ICA to lie close to the man"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07766","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.07766/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:10:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HpR3tklZdekfSmgD7NhkEbDpzrccXfZN9prZObOm+eVlNOK3oGpJ9o4iXVeZR650oj9MCRYLpsaI7ORIjx7IBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:39:16.300255Z"},"content_sha256":"ebf3df9545a2c6afaec81744bda9e72550410eaff3bfda429ec6a565ff1fa81f","schema_version":"1.0","event_id":"sha256:ebf3df9545a2c6afaec81744bda9e72550410eaff3bfda429ec6a565ff1fa81f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WDQ2LMI2RDD3IBWTDPHVFMLSB/bundle.json","state_url":"https://pith.science/pith/7WDQ2LMI2RDD3IBWTDPHVFMLSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WDQ2LMI2RDD3IBWTDPHVFMLSB/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":"2026-08-04T04:39:16Z","links":{"resolver":"https://pith.science/pith/7WDQ2LMI2RDD3IBWTDPHVFMLSB","bundle":"https://pith.science/pith/7WDQ2LMI2RDD3IBWTDPHVFMLSB/bundle.json","state":"https://pith.science/pith/7WDQ2LMI2RDD3IBWTDPHVFMLSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WDQ2LMI2RDD3IBWTDPHVFMLSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7WDQ2LMI2RDD3IBWTDPHVFMLSB","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":"136b459103365d5e7b7920c99124a49048f7700829510633be4a7b690086fb3d","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-18T17:58:07Z","title_canon_sha256":"b7b9a39da9fc0c6064376f7e1e75b32315a7e2e4b735bc79456eedd7ba0a0499"},"schema_version":"1.0","source":{"id":"2002.07766","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.07766","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"2002.07766v5","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07766","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"7WDQ2LMI2RDD","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"pith_short_16","alias_value":"7WDQ2LMI2RDD3IBW","created_at":"2026-07-05T02:10:37Z"},{"alias_kind":"pith_short_8","alias_value":"7WDQ2LMI","created_at":"2026-07-05T02:10:37Z"}],"graph_snapshots":[{"event_id":"sha256:ebf3df9545a2c6afaec81744bda9e72550410eaff3bfda429ec6a565ff1fa81f","target":"graph","created_at":"2026-07-05T02:10:37Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.07766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Separating high-dimensional data like images into independent latent factors, i.e independent component analysis (ICA), remains an open research problem. As we show, existing probabilistic deep generative models (DGMs), which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. Given the complexities of jointly training such a hybrid model, we introduce novel theory that constrains linear ICA to lie close to the man","authors_text":"Alexander Camuto, Brooks Paige, Chris Holmes, Matthew Willetts, Stephen Roberts","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-18T17:58:07Z","title":"Learning Bijective Feature Maps for Linear ICA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07766","kind":"arxiv","version":5},"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":"sha256:40a92b77a67cf6934c20c95bc2f057a030371e3678ce52b6da671ac39448f610","target":"record","created_at":"2026-07-05T02:10:37Z","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":"136b459103365d5e7b7920c99124a49048f7700829510633be4a7b690086fb3d","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-18T17:58:07Z","title_canon_sha256":"b7b9a39da9fc0c6064376f7e1e75b32315a7e2e4b735bc79456eedd7ba0a0499"},"schema_version":"1.0","source":{"id":"2002.07766","kind":"arxiv","version":5}},"canonical_sha256":"fd870d2d88d4463da03698de7a958b905722127bcbd13e69916d8ee486a33e0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd870d2d88d4463da03698de7a958b905722127bcbd13e69916d8ee486a33e0e","first_computed_at":"2026-07-05T02:10:37.764157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:10:37.764157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uv/Uc09FUz4j5OOpFewaLr0gNBHvDG1SDTdMYEoqvj3XfHhooE9wmNFGfkS7c2geRI3fdiXUelV+IcB3yk54Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:10:37.764624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.07766","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40a92b77a67cf6934c20c95bc2f057a030371e3678ce52b6da671ac39448f610","sha256:ebf3df9545a2c6afaec81744bda9e72550410eaff3bfda429ec6a565ff1fa81f"],"state_sha256":"33d2c0bd6ed5b70bc184037fd89575e9e502c2df47fc0f158c18ef9d32d3ae01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VG9P8w2Jma4mTwvInXm2csKDSAxin3nKqh2tG0p1XcpK9tion4lmH0r3y7GBBpPstlnT7jrLt2X20ZjOxR17Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:39:16.304176Z","bundle_sha256":"dcf84a04be7d5a286ad98be700768c982d0edb844dcc92f0e26a3ddb1e309620"}}