{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DWVABLBXCJP7WG57TYBFNG7NDJ","short_pith_number":"pith:DWVABLBX","schema_version":"1.0","canonical_sha256":"1daa00ac37125ffb1bbf9e02569bed1a5ee8d0596b692d9554287468a77ea7f1","source":{"kind":"arxiv","id":"1909.13327","version":1},"attestation_state":"computed","paper":{"title":"Natural representation of composite data with replicated autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-bio.QM","authors_text":"Carlo Baldassi, Christoph Feinauer, Davide Bergamini, Matteo Negri, Riccardo Zecchina","submitted_at":"2019-09-29T17:41:44Z","abstract_excerpt":"Generative processes in biology and other fields often produce data that can be regarded as resulting from a composition of basic features. Here we present an unsupervised method based on autoencoders for inferring these basic features of data. The main novelty in our approach is that the training is based on the optimization of the `local entropy' rather than the standard loss, resulting in a more robust inference, and enhancing the performance on this type of data considerably. Algorithmically, this is realized by training an interacting system of replicated autoencoders. We apply this metho"},"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":"1909.13327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2019-09-29T17:41:44Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a2680d37adf00ce5e85930863986b412555741afe461518b2acdbc52936131d7","abstract_canon_sha256":"b9b97156b6328ed2927cbd861633636442bc51e2d3f95007e79e96647a7106c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:09:27.110635Z","signature_b64":"j4k0RJJTFgiORag6Gf1WVTu39HXMdHDQlVM04LweNZC9JfN/NEjh57fhpl+TWL1w1OqzhyMjNcH3M8KvShmFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1daa00ac37125ffb1bbf9e02569bed1a5ee8d0596b692d9554287468a77ea7f1","last_reissued_at":"2026-07-05T00:09:27.110123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:09:27.110123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural representation of composite data with replicated autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-bio.QM","authors_text":"Carlo Baldassi, Christoph Feinauer, Davide Bergamini, Matteo Negri, Riccardo Zecchina","submitted_at":"2019-09-29T17:41:44Z","abstract_excerpt":"Generative processes in biology and other fields often produce data that can be regarded as resulting from a composition of basic features. Here we present an unsupervised method based on autoencoders for inferring these basic features of data. The main novelty in our approach is that the training is based on the optimization of the `local entropy' rather than the standard loss, resulting in a more robust inference, and enhancing the performance on this type of data considerably. Algorithmically, this is realized by training an interacting system of replicated autoencoders. We apply this metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13327","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/1909.13327/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":"1909.13327","created_at":"2026-07-05T00:09:27.110191+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.13327v1","created_at":"2026-07-05T00:09:27.110191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13327","created_at":"2026-07-05T00:09:27.110191+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWVABLBXCJP7","created_at":"2026-07-05T00:09:27.110191+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWVABLBXCJP7WG57","created_at":"2026-07-05T00:09:27.110191+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWVABLBX","created_at":"2026-07-05T00:09:27.110191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ","json":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ.json","graph_json":"https://pith.science/api/pith-number/DWVABLBXCJP7WG57TYBFNG7NDJ/graph.json","events_json":"https://pith.science/api/pith-number/DWVABLBXCJP7WG57TYBFNG7NDJ/events.json","paper":"https://pith.science/paper/DWVABLBX"},"agent_actions":{"view_html":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ","download_json":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ.json","view_paper":"https://pith.science/paper/DWVABLBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.13327&json=true","fetch_graph":"https://pith.science/api/pith-number/DWVABLBXCJP7WG57TYBFNG7NDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DWVABLBXCJP7WG57TYBFNG7NDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ/action/storage_attestation","attest_author":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ/action/author_attestation","sign_citation":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ/action/citation_signature","submit_replication":"https://pith.science/pith/DWVABLBXCJP7WG57TYBFNG7NDJ/action/replication_record"}},"created_at":"2026-07-05T00:09:27.110191+00:00","updated_at":"2026-07-05T00:09:27.110191+00:00"}