{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:64UN4WQMXAEKX47O2VQQ762QCU","short_pith_number":"pith:64UN4WQM","schema_version":"1.0","canonical_sha256":"f728de5a0cb808abf3eed5610ffb50152437839f61e31b8386154d04aa382b51","source":{"kind":"arxiv","id":"2410.21869","version":3},"attestation_state":"computed","paper":{"title":"Cross-Entropy Is All You Need To Invert the Data Generating Process","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alice Bizeul, Attila Juhos, David Klindt, Julia E. Vogt, Patrik Reizinger, Randall Balestriero, Wieland Brendel","submitted_at":"2024-10-29T09:03:57Z","abstract_excerpt":"Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neural analogy-making and the linear representation hypothesis, suggest that supervised models can learn interpretable factors of variation in a linear fashion. Recent advances in self-supervised learning, particularly nonlinear Independent Component Analysis, have shown that these methods can recover latent structures by inverting the data generating process. We extend these identifiability results to parametric instance"},"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":"2410.21869","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T09:03:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9a71ee654475fda43322461488bfa96839ac4da07c1f1fafa62e7f4f4f9c6afa","abstract_canon_sha256":"c9ad49ac5f5db04fd2a04ab738b8c605b2e87040d23f9c098e79289816c6278e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:30.444468Z","signature_b64":"2py7Cnda4faWFSxzbp/a6JRbaswU/Ru9Y7HqKHFJ5agrAhH7kOGSLOJ4E/xeNdh2tLk11XaB2vVtaorUBN54Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f728de5a0cb808abf3eed5610ffb50152437839f61e31b8386154d04aa382b51","last_reissued_at":"2026-07-05T10:19:30.444011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:30.444011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Entropy Is All You Need To Invert the Data Generating Process","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alice Bizeul, Attila Juhos, David Klindt, Julia E. Vogt, Patrik Reizinger, Randall Balestriero, Wieland Brendel","submitted_at":"2024-10-29T09:03:57Z","abstract_excerpt":"Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neural analogy-making and the linear representation hypothesis, suggest that supervised models can learn interpretable factors of variation in a linear fashion. Recent advances in self-supervised learning, particularly nonlinear Independent Component Analysis, have shown that these methods can recover latent structures by inverting the data generating process. We extend these identifiability results to parametric instance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21869","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.21869/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":"2410.21869","created_at":"2026-07-05T10:19:30.444070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21869v3","created_at":"2026-07-05T10:19:30.444070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21869","created_at":"2026-07-05T10:19:30.444070+00:00"},{"alias_kind":"pith_short_12","alias_value":"64UN4WQMXAEK","created_at":"2026-07-05T10:19:30.444070+00:00"},{"alias_kind":"pith_short_16","alias_value":"64UN4WQMXAEKX47O","created_at":"2026-07-05T10:19:30.444070+00:00"},{"alias_kind":"pith_short_8","alias_value":"64UN4WQM","created_at":"2026-07-05T10:19:30.444070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26379","citing_title":"When Does LeJEPA Learn a World Model?","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03517","citing_title":"Understanding Self-Supervised Learning via Latent Distribution Matching","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21058","citing_title":"A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03517","citing_title":"Understanding Self-Supervised Learning via Latent Distribution Matching","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":248,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16412","citing_title":"SCAR: Self-Supervised Continuous Action Representation Learning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03517","citing_title":"Understanding Self-Supervised Learning via Latent Distribution Matching","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21691","citing_title":"There Will Be a Scientific Theory of Deep Learning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU","json":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU.json","graph_json":"https://pith.science/api/pith-number/64UN4WQMXAEKX47O2VQQ762QCU/graph.json","events_json":"https://pith.science/api/pith-number/64UN4WQMXAEKX47O2VQQ762QCU/events.json","paper":"https://pith.science/paper/64UN4WQM"},"agent_actions":{"view_html":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU","download_json":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU.json","view_paper":"https://pith.science/paper/64UN4WQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21869&json=true","fetch_graph":"https://pith.science/api/pith-number/64UN4WQMXAEKX47O2VQQ762QCU/graph.json","fetch_events":"https://pith.science/api/pith-number/64UN4WQMXAEKX47O2VQQ762QCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU/action/storage_attestation","attest_author":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU/action/author_attestation","sign_citation":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU/action/citation_signature","submit_replication":"https://pith.science/pith/64UN4WQMXAEKX47O2VQQ762QCU/action/replication_record"}},"created_at":"2026-07-05T10:19:30.444070+00:00","updated_at":"2026-07-05T10:19:30.444070+00:00"}