{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:75WWH63R6ITC7JL3VLBBP5QB4Z","short_pith_number":"pith:75WWH63R","schema_version":"1.0","canonical_sha256":"ff6d63fb71f2262fa57baac217f601e67f512d81486522dfba6d4b05fc9036b6","source":{"kind":"arxiv","id":"2204.02283","version":2},"attestation_state":"computed","paper":{"title":"Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Casimir J.H. Ludwig, Gaurav Malhotra, Jeffrey S. Bowers, Milton L. Montero, Rui Ponte Costa","submitted_at":"2022-04-05T15:31:06Z","abstract_excerpt":"Recent research has shown that generative models with highly disentangled representations fail to generalise to unseen combination of generative factor values. These findings contradict earlier research which showed improved performance in out-of-training distribution settings when compared to entangled representations. Additionally, it is not clear if the reported failures are due to (a) encoders failing to map novel combinations to the proper regions of the latent space or (b) novel combinations being mapped correctly but the decoder/downstream process is unable to render the correct output "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.02283","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-05T15:31:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a527a95650993ac3c91f9c4a0d1ed33214271ab7fa2f71b30223117d5639620a","abstract_canon_sha256":"08c396401d1431ed69720101a610c1d3e0d49dcd5d2550fab373c156dbc6cac9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:38.069612Z","signature_b64":"0LMzyBmtM3lBWnt3pochd3iFfZwJWbVM53c/H0L1AxxgRNbySSZq2OLsjF17wgNW75LGj9r2NTXaY3+RzKU/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff6d63fb71f2262fa57baac217f601e67f512d81486522dfba6d4b05fc9036b6","last_reissued_at":"2026-07-05T08:31:38.069181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:38.069181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Casimir J.H. Ludwig, Gaurav Malhotra, Jeffrey S. Bowers, Milton L. Montero, Rui Ponte Costa","submitted_at":"2022-04-05T15:31:06Z","abstract_excerpt":"Recent research has shown that generative models with highly disentangled representations fail to generalise to unseen combination of generative factor values. These findings contradict earlier research which showed improved performance in out-of-training distribution settings when compared to entangled representations. Additionally, it is not clear if the reported failures are due to (a) encoders failing to map novel combinations to the proper regions of the latent space or (b) novel combinations being mapped correctly but the decoder/downstream process is unable to render the correct output "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02283","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.02283/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.02283","created_at":"2026-07-05T08:31:38.069242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02283v2","created_at":"2026-07-05T08:31:38.069242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02283","created_at":"2026-07-05T08:31:38.069242+00:00"},{"alias_kind":"pith_short_12","alias_value":"75WWH63R6ITC","created_at":"2026-07-05T08:31:38.069242+00:00"},{"alias_kind":"pith_short_16","alias_value":"75WWH63R6ITC7JL3","created_at":"2026-07-05T08:31:38.069242+00:00"},{"alias_kind":"pith_short_8","alias_value":"75WWH63R","created_at":"2026-07-05T08:31:38.069242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":292,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z","json":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z.json","graph_json":"https://pith.science/api/pith-number/75WWH63R6ITC7JL3VLBBP5QB4Z/graph.json","events_json":"https://pith.science/api/pith-number/75WWH63R6ITC7JL3VLBBP5QB4Z/events.json","paper":"https://pith.science/paper/75WWH63R"},"agent_actions":{"view_html":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z","download_json":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z.json","view_paper":"https://pith.science/paper/75WWH63R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02283&json=true","fetch_graph":"https://pith.science/api/pith-number/75WWH63R6ITC7JL3VLBBP5QB4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/75WWH63R6ITC7JL3VLBBP5QB4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z/action/storage_attestation","attest_author":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z/action/author_attestation","sign_citation":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z/action/citation_signature","submit_replication":"https://pith.science/pith/75WWH63R6ITC7JL3VLBBP5QB4Z/action/replication_record"}},"created_at":"2026-07-05T08:31:38.069242+00:00","updated_at":"2026-07-05T08:31:38.069242+00:00"}