{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MAFHNYSI4BGLZORS4746UPNUL5","short_pith_number":"pith:MAFHNYSI","schema_version":"1.0","canonical_sha256":"600a76e248e04cbcba32e7f9ea3db45f4f0157e6da60643d32325b99a5577e0e","source":{"kind":"arxiv","id":"2310.02250","version":3},"attestation_state":"computed","paper":{"title":"Why should autoencoders work?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eduardo D. Sontag, Matthew D. Kvalheim","submitted_at":"2023-10-03T17:53:43Z","abstract_excerpt":"Deep neural network autoencoders are routinely used computationally for model reduction. They allow recognizing the intrinsic dimension of data that lie in a $k$-dimensional subset $K$ of an input Euclidean space $\\mathbb{R}^n$. The underlying idea is to obtain both an encoding layer that maps $\\mathbb{R}^n$ into $\\mathbb{R}^k$ (called the bottleneck layer or the space of latent variables) and a decoding layer that maps $\\mathbb{R}^k$ back into $\\mathbb{R}^n$, in such a way that the input data from the set $K$ is recovered when composing the two maps. This is achieved by adjusting parameters ("},"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":"2310.02250","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T17:53:43Z","cross_cats_sorted":[],"title_canon_sha256":"0e115c985828be11eadacf41f5938d307cdfbf0ba23319959ab95df69e82efed","abstract_canon_sha256":"1b996799f25ff14ec536b1591824441bc41e399e9af502940e16b8528da7a192"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:23.719624Z","signature_b64":"lq2cXeYVRkQZNBWIQYc0+/3u7av/ITEqQXpBWFXrX4vHeW/IbZwGQnHn+Gb9inHhd6sr+NfvNNQKJgCUMdQWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"600a76e248e04cbcba32e7f9ea3db45f4f0157e6da60643d32325b99a5577e0e","last_reissued_at":"2026-07-05T07:46:23.719214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:23.719214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why should autoencoders work?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eduardo D. Sontag, Matthew D. Kvalheim","submitted_at":"2023-10-03T17:53:43Z","abstract_excerpt":"Deep neural network autoencoders are routinely used computationally for model reduction. They allow recognizing the intrinsic dimension of data that lie in a $k$-dimensional subset $K$ of an input Euclidean space $\\mathbb{R}^n$. The underlying idea is to obtain both an encoding layer that maps $\\mathbb{R}^n$ into $\\mathbb{R}^k$ (called the bottleneck layer or the space of latent variables) and a decoding layer that maps $\\mathbb{R}^k$ back into $\\mathbb{R}^n$, in such a way that the input data from the set $K$ is recovered when composing the two maps. This is achieved by adjusting parameters ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02250","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/2310.02250/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":"2310.02250","created_at":"2026-07-05T07:46:23.719279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02250v3","created_at":"2026-07-05T07:46:23.719279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02250","created_at":"2026-07-05T07:46:23.719279+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAFHNYSI4BGL","created_at":"2026-07-05T07:46:23.719279+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAFHNYSI4BGLZORS","created_at":"2026-07-05T07:46:23.719279+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAFHNYSI","created_at":"2026-07-05T07:46:23.719279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10857","citing_title":"FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5","json":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5.json","graph_json":"https://pith.science/api/pith-number/MAFHNYSI4BGLZORS4746UPNUL5/graph.json","events_json":"https://pith.science/api/pith-number/MAFHNYSI4BGLZORS4746UPNUL5/events.json","paper":"https://pith.science/paper/MAFHNYSI"},"agent_actions":{"view_html":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5","download_json":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5.json","view_paper":"https://pith.science/paper/MAFHNYSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02250&json=true","fetch_graph":"https://pith.science/api/pith-number/MAFHNYSI4BGLZORS4746UPNUL5/graph.json","fetch_events":"https://pith.science/api/pith-number/MAFHNYSI4BGLZORS4746UPNUL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5/action/storage_attestation","attest_author":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5/action/author_attestation","sign_citation":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5/action/citation_signature","submit_replication":"https://pith.science/pith/MAFHNYSI4BGLZORS4746UPNUL5/action/replication_record"}},"created_at":"2026-07-05T07:46:23.719279+00:00","updated_at":"2026-07-05T07:46:23.719279+00:00"}