{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:K24VAC2ZFAZOKXRU45OTILT7RE","short_pith_number":"pith:K24VAC2Z","schema_version":"1.0","canonical_sha256":"56b9500b592832e55e34e75d342e7f891ea7fc0728370a244054ca568e118d49","source":{"kind":"arxiv","id":"1211.4246","version":5},"attestation_state":"computed","paper":{"title":"What Regularized Auto-Encoders Learn from the Data Generating Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guillaume Alain, Yoshua Bengio","submitted_at":"2012-11-18T19:06:37Z","abstract_excerpt":"What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of data. This paper clarifies some of these previous observations by showing that minimizing a particular form of regularized reconstruction error yields a reconstruction function that locally characterizes the shape of the data generating density. We show that the auto-encoder captures the score (derivative of the log-density with respect to the input). It contradicts previous interpretations of reconstructi"},"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":"1211.4246","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-11-18T19:06:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"924050f95a8a39c18b481682fdac78f6d500fdd1ebcf563d732c4504e2a3449c","abstract_canon_sha256":"59d8e18a27fb139816ff50ff45a3d06017caf9870ae8d29afedef87a215c9127"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:57.024918Z","signature_b64":"EeTjAhjTn8OVswRUNeICwyDI6FPWtHwKHrwqxHWFDRJAdIbGoLXiTj50FfAvtKTQscBi4F6wArZ7PzTXAXcvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56b9500b592832e55e34e75d342e7f891ea7fc0728370a244054ca568e118d49","last_reissued_at":"2026-05-18T02:44:57.024440Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:57.024440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Regularized Auto-Encoders Learn from the Data Generating Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guillaume Alain, Yoshua Bengio","submitted_at":"2012-11-18T19:06:37Z","abstract_excerpt":"What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of data. This paper clarifies some of these previous observations by showing that minimizing a particular form of regularized reconstruction error yields a reconstruction function that locally characterizes the shape of the data generating density. We show that the auto-encoder captures the score (derivative of the log-density with respect to the input). It contradicts previous interpretations of reconstructi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1211.4246","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":""},"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":"1211.4246","created_at":"2026-05-18T02:44:57.024513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1211.4246v5","created_at":"2026-05-18T02:44:57.024513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.4246","created_at":"2026-05-18T02:44:57.024513+00:00"},{"alias_kind":"pith_short_12","alias_value":"K24VAC2ZFAZO","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_16","alias_value":"K24VAC2ZFAZOKXRU","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_8","alias_value":"K24VAC2Z","created_at":"2026-05-18T12:27:11.947152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.14876","citing_title":"Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE","json":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE.json","graph_json":"https://pith.science/api/pith-number/K24VAC2ZFAZOKXRU45OTILT7RE/graph.json","events_json":"https://pith.science/api/pith-number/K24VAC2ZFAZOKXRU45OTILT7RE/events.json","paper":"https://pith.science/paper/K24VAC2Z"},"agent_actions":{"view_html":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE","download_json":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE.json","view_paper":"https://pith.science/paper/K24VAC2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1211.4246&json=true","fetch_graph":"https://pith.science/api/pith-number/K24VAC2ZFAZOKXRU45OTILT7RE/graph.json","fetch_events":"https://pith.science/api/pith-number/K24VAC2ZFAZOKXRU45OTILT7RE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE/action/storage_attestation","attest_author":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE/action/author_attestation","sign_citation":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE/action/citation_signature","submit_replication":"https://pith.science/pith/K24VAC2ZFAZOKXRU45OTILT7RE/action/replication_record"}},"created_at":"2026-05-18T02:44:57.024513+00:00","updated_at":"2026-05-18T02:44:57.024513+00:00"}