{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TN7D5FA45HJ5OTMZE5HY7LC76J","short_pith_number":"pith:TN7D5FA4","schema_version":"1.0","canonical_sha256":"9b7e3e941ce9d3d74d99274f8fac5ff26db542835ed8f835dc6d9ecfaf2cf67c","source":{"kind":"arxiv","id":"2506.19104","version":1},"attestation_state":"computed","paper":{"title":"On the algorithmic construction of deep ReLU networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Daan Huybrechs","submitted_at":"2025-06-23T20:35:52Z","abstract_excerpt":"It is difficult to describe in mathematical terms what a neural network trained on data represents. On the other hand, there is a growing mathematical understanding of what neural networks are in principle capable of representing. Feedforward neural networks using the ReLU activation function represent continuous and piecewise linear functions and can approximate many others. The study of their expressivity addresses the question: which ones? Contributing to the available answers, we take the perspective of a neural network as an algorithm. In this analogy, a neural network is programmed const"},"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":"2506.19104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T20:35:52Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"f323d17346d80b0beaddbfbb01a12cd8ccc4adc65bbcda19f3102e469a961139","abstract_canon_sha256":"fe6906f0c668411afb7be4334cab1e2722f3944230b5faa8f83258bdf0c715e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:09.478795Z","signature_b64":"hCn5yjMoONQ5WJXptOEC14zHnQqZFbumoPfqhAZvAChZjcQ62k5SwYP6stqeYxXTVbEAV9YEsq2EQgeB6LQXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b7e3e941ce9d3d74d99274f8fac5ff26db542835ed8f835dc6d9ecfaf2cf67c","last_reissued_at":"2026-07-05T11:26:09.478358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:09.478358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the algorithmic construction of deep ReLU networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Daan Huybrechs","submitted_at":"2025-06-23T20:35:52Z","abstract_excerpt":"It is difficult to describe in mathematical terms what a neural network trained on data represents. On the other hand, there is a growing mathematical understanding of what neural networks are in principle capable of representing. Feedforward neural networks using the ReLU activation function represent continuous and piecewise linear functions and can approximate many others. The study of their expressivity addresses the question: which ones? Contributing to the available answers, we take the perspective of a neural network as an algorithm. In this analogy, a neural network is programmed const"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19104","kind":"arxiv","version":1},"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/2506.19104/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":"2506.19104","created_at":"2026-07-05T11:26:09.478419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19104v1","created_at":"2026-07-05T11:26:09.478419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19104","created_at":"2026-07-05T11:26:09.478419+00:00"},{"alias_kind":"pith_short_12","alias_value":"TN7D5FA45HJ5","created_at":"2026-07-05T11:26:09.478419+00:00"},{"alias_kind":"pith_short_16","alias_value":"TN7D5FA45HJ5OTMZ","created_at":"2026-07-05T11:26:09.478419+00:00"},{"alias_kind":"pith_short_8","alias_value":"TN7D5FA4","created_at":"2026-07-05T11:26:09.478419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J","json":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J.json","graph_json":"https://pith.science/api/pith-number/TN7D5FA45HJ5OTMZE5HY7LC76J/graph.json","events_json":"https://pith.science/api/pith-number/TN7D5FA45HJ5OTMZE5HY7LC76J/events.json","paper":"https://pith.science/paper/TN7D5FA4"},"agent_actions":{"view_html":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J","download_json":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J.json","view_paper":"https://pith.science/paper/TN7D5FA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19104&json=true","fetch_graph":"https://pith.science/api/pith-number/TN7D5FA45HJ5OTMZE5HY7LC76J/graph.json","fetch_events":"https://pith.science/api/pith-number/TN7D5FA45HJ5OTMZE5HY7LC76J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J/action/storage_attestation","attest_author":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J/action/author_attestation","sign_citation":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J/action/citation_signature","submit_replication":"https://pith.science/pith/TN7D5FA45HJ5OTMZE5HY7LC76J/action/replication_record"}},"created_at":"2026-07-05T11:26:09.478419+00:00","updated_at":"2026-07-05T11:26:09.478419+00:00"}