{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Y7T67HXSZOUO3YAFK2XJVH2QCZ","short_pith_number":"pith:Y7T67HXS","canonical_record":{"source":{"id":"2605.22531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T14:22:25Z","cross_cats_sorted":[],"title_canon_sha256":"c688c22c40157d9e13390acc1428e840c069f4d74ac5e5dc3281fdfc31735475","abstract_canon_sha256":"50e78cf8cb8adeaaabb055a2269164681b143faf00cfbd23d211672d5a45b34a"},"schema_version":"1.0"},"canonical_sha256":"c7e7ef9ef2cba8ede00556ae9a9f501669b9d7c0946de251321365159b206734","source":{"kind":"arxiv","id":"2605.22531","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22531","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22531v1","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22531","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"Y7T67HXSZOUO","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"Y7T67HXSZOUO3YAF","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"Y7T67HXS","created_at":"2026-05-22T01:04:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Y7T67HXSZOUO3YAFK2XJVH2QCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T14:22:25Z","cross_cats_sorted":[],"title_canon_sha256":"c688c22c40157d9e13390acc1428e840c069f4d74ac5e5dc3281fdfc31735475","abstract_canon_sha256":"50e78cf8cb8adeaaabb055a2269164681b143faf00cfbd23d211672d5a45b34a"},"schema_version":"1.0"},"canonical_sha256":"c7e7ef9ef2cba8ede00556ae9a9f501669b9d7c0946de251321365159b206734","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:55.745350Z","signature_b64":"3D2pGRzAt54Ngu3yyGexncy6k21r4N+ZQCcZdtvy4iti/WzuYGtSb5COeCT4hTQsnuXg/7XFxf1/RGfUwS8ZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7e7ef9ef2cba8ede00556ae9a9f501669b9d7c0946de251321365159b206734","last_reissued_at":"2026-05-22T01:04:55.744249Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:55.744249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22531","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":"2026-05-22T01:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNuqq1jLwLUCGXXGyny8dRl2/1ADil678Vuo11XZl+2xpOOTMkiTDTNQqx5fnNTbwszy4tmm7zL1mdq/VdhmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:06:11.505053Z"},"content_sha256":"348b15436a6e43bec0e4304bbb7df9ad543b621c958a798bee762b559e743eb8","schema_version":"1.0","event_id":"sha256:348b15436a6e43bec0e4304bbb7df9ad543b621c958a798bee762b559e743eb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Y7T67HXSZOUO3YAFK2XJVH2QCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentanglement Beyond Generative Models with Riemannian ICA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Edmond Cunningham","submitted_at":"2026-05-21T14:22:25Z","abstract_excerpt":"There is a gap between the theoretical foundations of disentanglement and the practice of modern representation learning. Existing theoretical frameworks, particularly Independent Component Analysis (ICA) and its nonlinear variants, assume a generative model with statistically independent latent variables underlying the data so that disentanglement amounts to identifying the latents that could have generated the data. This generative framework is interpretable and theoretically justified, but its strong assumptions make it difficult to apply to modern representation learning. Modern pretrained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22531","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.22531/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":"2026-05-22T01:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTY0IeNYAz9BkIKfOiu3dXGpXr+wwE7mzSX9vxKVp3FZaqfZcghorVaZxRfdJdtgHpPg2gV9ecxO/QLzdkzkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:06:11.505530Z"},"content_sha256":"860025f66ba22b1972776daecfb48b8b8b060e2498a59e476172e1cfbc84f1e6","schema_version":"1.0","event_id":"sha256:860025f66ba22b1972776daecfb48b8b8b060e2498a59e476172e1cfbc84f1e6"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:Y7T67HXSZOUO3YAFK2XJVH2QCZ","target":"integrity","payload":{"note":"Identifier '10.1016/s0893-6080(00' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Aapo Hyvärinen and Erkki Oja. Independent component analysis: Algorithms and applications. Neural Networks, 13(4–5):411–430, 6 2000. ISSN 0893-6080. doi: 10.1016/S0893-6080(00) 00026-5. 13","arxiv_id":"2605.22531","detector":"doi_compliance","evidence":{"doi":"10.1016/s0893-6080(00","arxiv_id":null,"ref_index":41,"raw_excerpt":"Aapo Hyvärinen and Erkki Oja. Independent component analysis: Algorithms and applications. Neural Networks, 13(4–5):411–430, 6 2000. ISSN 0893-6080. doi: 10.1016/S0893-6080(00) 00026-5. 13","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":41,"audited_at":"2026-05-22T07:49:54.775008Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/s0893-6080(00","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"027c91ecf8877c19ffd0abba963bf9b4b9196991c887346c7351307b2d37e4eb","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":6284,"payload_sha256":"c6deea2edaf79e2a958b4c563a2c8ad57156da538bcc9e72674541284685bcef","signature_b64":"1FmfY7psUa3vwQk3Yjltauyp3VQQPRmR7HhzkV+RTjhph2n5F6PDFQhjY2m2Ra9GyHVw7UMJRjcaWGlAvUVhDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T07:50:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vSHw7/zNsqlRGgz+75z2sxZSOboir/8m7ss3H/dXlg13sZOYp78f/dPHUCI9Z1XltjTC/wfnXO0/doocXIpNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:06:11.506834Z"},"content_sha256":"38a2b78d44dc4661f28ee4c4399acaa21bb8aff8ec56bcd9b335d873f635385d","schema_version":"1.0","event_id":"sha256:38a2b78d44dc4661f28ee4c4399acaa21bb8aff8ec56bcd9b335d873f635385d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7T67HXSZOUO3YAFK2XJVH2QCZ/bundle.json","state_url":"https://pith.science/pith/Y7T67HXSZOUO3YAFK2XJVH2QCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7T67HXSZOUO3YAFK2XJVH2QCZ/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":"2026-05-25T15:06:11Z","links":{"resolver":"https://pith.science/pith/Y7T67HXSZOUO3YAFK2XJVH2QCZ","bundle":"https://pith.science/pith/Y7T67HXSZOUO3YAFK2XJVH2QCZ/bundle.json","state":"https://pith.science/pith/Y7T67HXSZOUO3YAFK2XJVH2QCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7T67HXSZOUO3YAFK2XJVH2QCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y7T67HXSZOUO3YAFK2XJVH2QCZ","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"50e78cf8cb8adeaaabb055a2269164681b143faf00cfbd23d211672d5a45b34a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T14:22:25Z","title_canon_sha256":"c688c22c40157d9e13390acc1428e840c069f4d74ac5e5dc3281fdfc31735475"},"schema_version":"1.0","source":{"id":"2605.22531","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22531","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22531v1","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22531","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"Y7T67HXSZOUO","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"Y7T67HXSZOUO3YAF","created_at":"2026-05-22T01:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"Y7T67HXS","created_at":"2026-05-22T01:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:860025f66ba22b1972776daecfb48b8b8b060e2498a59e476172e1cfbc84f1e6","target":"graph","created_at":"2026-05-22T01:04:55Z","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/2605.22531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a gap between the theoretical foundations of disentanglement and the practice of modern representation learning. Existing theoretical frameworks, particularly Independent Component Analysis (ICA) and its nonlinear variants, assume a generative model with statistically independent latent variables underlying the data so that disentanglement amounts to identifying the latents that could have generated the data. This generative framework is interpretable and theoretically justified, but its strong assumptions make it difficult to apply to modern representation learning. Modern pretrained","authors_text":"Edmond Cunningham","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T14:22:25Z","title":"Disentanglement Beyond Generative Models with Riemannian ICA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22531","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":"sha256:348b15436a6e43bec0e4304bbb7df9ad543b621c958a798bee762b559e743eb8","target":"record","created_at":"2026-05-22T01:04:55Z","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":"50e78cf8cb8adeaaabb055a2269164681b143faf00cfbd23d211672d5a45b34a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T14:22:25Z","title_canon_sha256":"c688c22c40157d9e13390acc1428e840c069f4d74ac5e5dc3281fdfc31735475"},"schema_version":"1.0","source":{"id":"2605.22531","kind":"arxiv","version":1}},"canonical_sha256":"c7e7ef9ef2cba8ede00556ae9a9f501669b9d7c0946de251321365159b206734","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7e7ef9ef2cba8ede00556ae9a9f501669b9d7c0946de251321365159b206734","first_computed_at":"2026-05-22T01:04:55.744249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:55.744249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3D2pGRzAt54Ngu3yyGexncy6k21r4N+ZQCcZdtvy4iti/WzuYGtSb5COeCT4hTQsnuXg/7XFxf1/RGfUwS8ZBQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:55.745350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22531","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:348b15436a6e43bec0e4304bbb7df9ad543b621c958a798bee762b559e743eb8","sha256:860025f66ba22b1972776daecfb48b8b8b060e2498a59e476172e1cfbc84f1e6","sha256:38a2b78d44dc4661f28ee4c4399acaa21bb8aff8ec56bcd9b335d873f635385d"],"state_sha256":"e14ef0712e3ac050e0e81543fb406fd2f89f29c3ac38860578d3b8fd12e9fa67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVHCZpFcKNP05Fb/9zbQ7Eo918Mj+nHMpIB5qHPwOIjNOwDZ3lRVQKsEyFm0RFpsT30VkLsI8nzhzp1S07hcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:06:11.509476Z","bundle_sha256":"fc5f6df0473601006cc28687c38597c9e8c604ae6509b4b191f3e2e614396db3"}}