{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JY2W6VKHBWISTMDP3HL6M3I4Y6","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":"011c30d32bcac545b1ed5a054adb5463bfd520c941354c465026fe21ad2d494b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T09:11:09Z","title_canon_sha256":"f2a818d9ff4464fe7aee4f1d98be2a7ac2073cdcb69bfe119601708c6ad90180"},"schema_version":"1.0","source":{"id":"2307.02129","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02129","created_at":"2026-07-05T08:39:27Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02129v5","created_at":"2026-07-05T08:39:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02129","created_at":"2026-07-05T08:39:27Z"},{"alias_kind":"pith_short_12","alias_value":"JY2W6VKHBWIS","created_at":"2026-07-05T08:39:27Z"},{"alias_kind":"pith_short_16","alias_value":"JY2W6VKHBWISTMDP","created_at":"2026-07-05T08:39:27Z"},{"alias_kind":"pith_short_8","alias_value":"JY2W6VKH","created_at":"2026-07-05T08:39:27Z"}],"graph_snapshots":[{"event_id":"sha256:6e3127ff28e3929851b3b8be0ff385f8865b6a2041a7a1a74af719ab58aeb084","target":"graph","created_at":"2026-07-05T08:39:27Z","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/2307.02129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional data representations. However, how many training examples are required to learn such representations remains unknown. To quantitatively study this question, we introduce the Random Hierarchy Model: a family of synthetic tasks inspired by the hierarchical structure of language and images. The model is a classification task where each class corresponds to a grou","authors_text":"Alessandro Favero, Francesco Cagnetta, Leonardo Petrini, Matthieu Wyart, Umberto M. Tomasini","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T09:11:09Z","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02129","kind":"arxiv","version":5},"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:a4db55068a3f706778773dd75d51c16af75bf6f571fe101df254d2ba1ee0b1d4","target":"record","created_at":"2026-07-05T08:39:27Z","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":"011c30d32bcac545b1ed5a054adb5463bfd520c941354c465026fe21ad2d494b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T09:11:09Z","title_canon_sha256":"f2a818d9ff4464fe7aee4f1d98be2a7ac2073cdcb69bfe119601708c6ad90180"},"schema_version":"1.0","source":{"id":"2307.02129","kind":"arxiv","version":5}},"canonical_sha256":"4e356f55470d9129b06fd9d7e66d1cc7a4ab13fbd9f76b29bf0d5c7e0938dd86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e356f55470d9129b06fd9d7e66d1cc7a4ab13fbd9f76b29bf0d5c7e0938dd86","first_computed_at":"2026-07-05T08:39:27.510736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:27.510736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rwnVvJ0ElVl8TN0HSPHZhyeWAVlGnu8HVp/e24DOx1MLmFIJOOktO8+mNJQ+D96UE3EVEzc8boc1DhcHT84rAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:27.511248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02129","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4db55068a3f706778773dd75d51c16af75bf6f571fe101df254d2ba1ee0b1d4","sha256:6e3127ff28e3929851b3b8be0ff385f8865b6a2041a7a1a74af719ab58aeb084"],"state_sha256":"1015c90b9351f7dd2d4b609f09e31c2e1333813db05f33763d0fddd37737ed32"}