{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OBLIM2QGROZ5NQWXHN23FE46QK","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":"e94abc874169e917d23672bb7b83eb0a47a4f560b435e4abb8e0a382f1b3b90e","cross_cats_sorted":["cs.AI","cs.LG","math.LO","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2025-09-22T17:00:40Z","title_canon_sha256":"000ef851dd27cbe3767c5a177d4a875adce63ab88bdd01d9dd8658dde3ecda31"},"schema_version":"1.0","source":{"id":"2509.18025","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.18025","created_at":"2026-06-02T02:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.18025v2","created_at":"2026-06-02T02:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.18025","created_at":"2026-06-02T02:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"OBLIM2QGROZ5","created_at":"2026-06-02T02:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"OBLIM2QGROZ5NQWX","created_at":"2026-06-02T02:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"OBLIM2QG","created_at":"2026-06-02T02:04:47Z"}],"graph_snapshots":[{"event_id":"sha256:b740f383ced78f1e607cbceb5cca8b8ab7424d64a4cdeed8784d1e98c377a311","target":"graph","created_at":"2026-06-02T02:04:47Z","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/2509.18025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One can see deep-learning models as compositions of functions within the so-called tame geometry. In this expository note, we give an overview of some topics at the interface of tame geometry (also known as o-minimality), optimization theory, and deep learning theory and practice. To do so, we gradually introduce the concepts and tools used to build convergence guarantees for stochastic gradient descent in a general nonsmooth nonconvex, but tame, setting. This illustrates some ways in which tame geometry is a natural mathematical framework for the study of AI systems, especially within Deep Le","authors_text":"Allen Gehret, Gilles Bareilles, Jakub Mare\\v{c}ek, Jana Lep\\v{s}ov\\'a, Johannes Aspman","cross_cats":["cs.AI","cs.LG","math.LO","stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2025-09-22T17:00:40Z","title":"Deep Learning as the Disciplined Construction of Tame Objects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.18025","kind":"arxiv","version":2},"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":"sha256:1eb5840ec11d114ee865eaa760b5f2bbc300f3cbb797f9f81cb1a9337129f15f","target":"record","created_at":"2026-06-02T02:04:47Z","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":"e94abc874169e917d23672bb7b83eb0a47a4f560b435e4abb8e0a382f1b3b90e","cross_cats_sorted":["cs.AI","cs.LG","math.LO","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2025-09-22T17:00:40Z","title_canon_sha256":"000ef851dd27cbe3767c5a177d4a875adce63ab88bdd01d9dd8658dde3ecda31"},"schema_version":"1.0","source":{"id":"2509.18025","kind":"arxiv","version":2}},"canonical_sha256":"7056866a068bb3d6c2d73b75b2939e82bdafaf7584cc67cb9cb4df6cd3af7d5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7056866a068bb3d6c2d73b75b2939e82bdafaf7584cc67cb9cb4df6cd3af7d5c","first_computed_at":"2026-06-02T02:04:47.891656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:47.891656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LHDH6hX5mqtAcBUabPEWhMnNiTIRR+BcqxSK7So1kpqyc2pDaiBX6TD5tjsSIJipt46xzMqYjt93BsPLRLdmCg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:47.892182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.18025","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1eb5840ec11d114ee865eaa760b5f2bbc300f3cbb797f9f81cb1a9337129f15f","sha256:b740f383ced78f1e607cbceb5cca8b8ab7424d64a4cdeed8784d1e98c377a311"],"state_sha256":"e4186b53f0b99bdd0df9325009c0ffe5cbd3b5d058ceebdbdf448fb1a1e0ce31"}