{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LGRTPP7LWI2RJMLXEUJ57QJZ5N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"98603ca80b14a326922099c8bfa2b4549d33eb85bf3ae9c1fc490dbedd50813a","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T16:32:29Z","title_canon_sha256":"352cf15b73a6e3bf7a8569b980c468108758ef8a4ec5cb8924f134cbffc581dd"},"schema_version":"1.0","source":{"id":"2402.05013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05013","created_at":"2026-07-05T07:42:35Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05013v1","created_at":"2026-07-05T07:42:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05013","created_at":"2026-07-05T07:42:35Z"},{"alias_kind":"pith_short_12","alias_value":"LGRTPP7LWI2R","created_at":"2026-07-05T07:42:35Z"},{"alias_kind":"pith_short_16","alias_value":"LGRTPP7LWI2RJMLX","created_at":"2026-07-05T07:42:35Z"},{"alias_kind":"pith_short_8","alias_value":"LGRTPP7L","created_at":"2026-07-05T07:42:35Z"}],"graph_snapshots":[{"event_id":"sha256:f93646329a0d50789cc67385eeaf611eb9ac497f8620e17929c146471b5f978c","target":"graph","created_at":"2026-07-05T07:42:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.05013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoencoders are a prominent model in many empirical branches of machine learning and lossy data compression. However, basic theoretical questions remain unanswered even in a shallow two-layer setting. In particular, to what degree does a shallow autoencoder capture the structure of the underlying data distribution? For the prototypical case of the 1-bit compression of sparse Gaussian data, we prove that gradient descent converges to a solution that completely disregards the sparse structure of the input. Namely, the performance of the algorithm is the same as if it was compressing a Gaussian ","authors_text":"Alexander Shevchenko, Hamed Hassani, Kevin K\\\"ogler, Marco Mondelli","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T16:32:29Z","title":"Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05013","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:40943ad57b195b80e165eefb618524dc145d58f8fc6e10f9e1be38cfd1afd4d5","target":"record","created_at":"2026-07-05T07:42:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"98603ca80b14a326922099c8bfa2b4549d33eb85bf3ae9c1fc490dbedd50813a","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T16:32:29Z","title_canon_sha256":"352cf15b73a6e3bf7a8569b980c468108758ef8a4ec5cb8924f134cbffc581dd"},"schema_version":"1.0","source":{"id":"2402.05013","kind":"arxiv","version":1}},"canonical_sha256":"59a337bfebb23514b1772513dfc139eb4ad92f506726ebc7999dc976321b2b84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59a337bfebb23514b1772513dfc139eb4ad92f506726ebc7999dc976321b2b84","first_computed_at":"2026-07-05T07:42:35.284608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:35.284608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aZK/NClQbNgxwmMd2NlmPiS38U2km0clQAdkRwTdzNa6lX1CAsbB4uknQccWTCTELsKfT2AfV6gQVSb8oc3PCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:35.285014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40943ad57b195b80e165eefb618524dc145d58f8fc6e10f9e1be38cfd1afd4d5","sha256:f93646329a0d50789cc67385eeaf611eb9ac497f8620e17929c146471b5f978c"],"state_sha256":"57978938a9b19e39b417d5dffc94c8fb0361c3b9d61740e4eff62ced5f7719b6"}