{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WO6K6PLUVNMOLJBKNTTXN26RPI","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":"92e4b40bdff1cbb037be38b9ce50c6252f26d448ee428d286b9bd75c63d9c6ef","cross_cats_sorted":["cs.AI","math-ph","math.MP","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T04:11:25Z","title_canon_sha256":"efb809716a2cf73addeef28f4bb323fa693dcc2daa1121d6878de9c7927cb5cf"},"schema_version":"1.0","source":{"id":"2311.07065","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07065","created_at":"2026-06-09T01:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07065v3","created_at":"2026-06-09T01:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07065","created_at":"2026-06-09T01:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"WO6K6PLUVNMO","created_at":"2026-06-09T01:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"WO6K6PLUVNMOLJBK","created_at":"2026-06-09T01:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"WO6K6PLU","created_at":"2026-06-09T01:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:f7c5e10350055522072e116b5d90f8c3989ec0e99ddad654b35a61131e65a622","target":"graph","created_at":"2026-06-09T01:05:02Z","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/2311.07065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We analyze geometric aspects of the gradient descent algorithm in Deep Learning (DL), and give a detailed discussion of the circumstance that in underparametrized DL networks, zero loss minimization can generically not be attained. As a consequence, we conclude that the distribution of training inputs must necessarily be non-generic in order to produce zero loss minimizers, both for the method constructed in [Chen-Munoz Ewald 2023, 2024], or for gradient descent [Chen 2025] (which assume clustering of training data).","authors_text":"Patricia Mu\\~noz Ewald, Thomas Chen","cross_cats":["cs.AI","math-ph","math.MP","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T04:11:25Z","title":"On non-approximability of zero loss global ${\\mathcal L}^2$ minimizers by gradient descent in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07065","kind":"arxiv","version":3},"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":"sha256:97fa854a1c2041238be8cb6c2e47ea542fa8b6111d54d0d0da8159d7ebc6fb26","target":"record","created_at":"2026-06-09T01:05:02Z","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":"92e4b40bdff1cbb037be38b9ce50c6252f26d448ee428d286b9bd75c63d9c6ef","cross_cats_sorted":["cs.AI","math-ph","math.MP","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T04:11:25Z","title_canon_sha256":"efb809716a2cf73addeef28f4bb323fa693dcc2daa1121d6878de9c7927cb5cf"},"schema_version":"1.0","source":{"id":"2311.07065","kind":"arxiv","version":3}},"canonical_sha256":"b3bcaf3d74ab58e5a42a6ce776ebd17a320206d6ea42f3476c7c502c09e46a0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3bcaf3d74ab58e5a42a6ce776ebd17a320206d6ea42f3476c7c502c09e46a0e","first_computed_at":"2026-06-09T01:05:02.973486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:02.973486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZsKgxFj8SlAs5qaSnW6Im0uFcCma61z15L35HpW9Ti9uSNpAFVJA9Sp5qLmj23rTkFtKreFfPD2pUaRONLTKDQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:02.973890Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07065","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97fa854a1c2041238be8cb6c2e47ea542fa8b6111d54d0d0da8159d7ebc6fb26","sha256:f7c5e10350055522072e116b5d90f8c3989ec0e99ddad654b35a61131e65a622"],"state_sha256":"d14089c6b4b3ddac1846041e0bf309eb23e968ade3e52098435f7c273d663404"}