{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NAV4IYYRS5U6TAH4MQHQH4WKN7","short_pith_number":"pith:NAV4IYYR","schema_version":"1.0","canonical_sha256":"682bc463119769e980fc640f03f2ca6ff98a186800d559c375fc728da1a17fc9","source":{"kind":"arxiv","id":"1605.07145","version":2},"attestation_state":"computed","paper":{"title":"On Optimality Conditions for Auto-Encoder Signal Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Devansh Arpit, Hung Q. Ngo, Nils Napp, Venu Govindaraju, Yingbo Zhou","submitted_at":"2016-05-23T19:21:53Z","abstract_excerpt":"Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sparse and distributed. On the other hand, compressed sensing and sparse coding assume a data generating process, where the observed data is generated from some true latent signal source, and try to recover the corresponding signal from measurements. Looking at auto-encoders from this \\textit{signal recovery perspective} enables us to have a more coherent view of these techniques. In this paper, in particular, we show "},"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":"1605.07145","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-23T19:21:53Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"f90f88bf85da497e5251b7127e5f954ed5d6cab8a7334490f9bbbf3e9f982e5f","abstract_canon_sha256":"49cb2d2867f3ad662f6f09d5ee02a84bdb0bf004ef7c7e8fdb767a96918ff163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:24.302910Z","signature_b64":"jXgUvdK0Fmo/zWFQxKOlRDdPb5hGb0vY+AofgUdIt8EPB8A1JFZexMkUJ46b6Bt1Q+SkZszA5MM+ldjKgKAxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"682bc463119769e980fc640f03f2ca6ff98a186800d559c375fc728da1a17fc9","last_reissued_at":"2026-05-18T00:40:24.302221Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:24.302221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Optimality Conditions for Auto-Encoder Signal Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Devansh Arpit, Hung Q. Ngo, Nils Napp, Venu Govindaraju, Yingbo Zhou","submitted_at":"2016-05-23T19:21:53Z","abstract_excerpt":"Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sparse and distributed. On the other hand, compressed sensing and sparse coding assume a data generating process, where the observed data is generated from some true latent signal source, and try to recover the corresponding signal from measurements. Looking at auto-encoders from this \\textit{signal recovery perspective} enables us to have a more coherent view of these techniques. In this paper, in particular, we show "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07145","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":""},"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":"1605.07145","created_at":"2026-05-18T00:40:24.302344+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.07145v2","created_at":"2026-05-18T00:40:24.302344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07145","created_at":"2026-05-18T00:40:24.302344+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAV4IYYRS5U6","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAV4IYYRS5U6TAH4","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAV4IYYR","created_at":"2026-05-18T12:30:32.724797+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/NAV4IYYRS5U6TAH4MQHQH4WKN7","json":"https://pith.science/pith/NAV4IYYRS5U6TAH4MQHQH4WKN7.json","graph_json":"https://pith.science/api/pith-number/NAV4IYYRS5U6TAH4MQHQH4WKN7/graph.json","events_json":"https://pith.science/api/pith-number/NAV4IYYRS5U6TAH4MQHQH4WKN7/events.json","paper":"https://pith.science/paper/NAV4IYYR"},"agent_actions":{"view_html":"https://pith.science/pith/NAV4IYYRS5U6TAH4MQHQH4WKN7","download_json":"https://pith.science/pith/NAV4IYYRS5U6TAH4MQHQH4WKN7.json","view_paper":"https://pith.science/paper/NAV4IYYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.07145&json=true","fetch_graph":"https://pith.science/api/pith-number/NAV4IYYRS5U6TAH4MQHQH4WKN7/graph.json","fetch_events":"https://pith.science/api/pith-number/NAV4IYYRS5U6TAH4MQHQH4WKN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAV4IYYRS5U6TAH4MQHQH4WKN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAV4IYYRS5U6TAH4MQHQH4WKN7/action/storage_attestation","attest_author":"https://pith.science/pith/NAV4IYYRS5U6TAH4MQHQH4WKN7/action/author_attestation","sign_citation":"https://pith.science/pith/NAV4IYYRS5U6TAH4MQHQH4WKN7/action/citation_signature","submit_replication":"https://pith.science/pith/NAV4IYYRS5U6TAH4MQHQH4WKN7/action/replication_record"}},"created_at":"2026-05-18T00:40:24.302344+00:00","updated_at":"2026-05-18T00:40:24.302344+00:00"}