{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:43R3DPKZ7CTJQ6U3DPYDYGOZZI","short_pith_number":"pith:43R3DPKZ","schema_version":"1.0","canonical_sha256":"e6e3b1bd59f8a6987a9b1bf03c19d9ca252f6e1f3fabb37d4bd47de7c3ff0486","source":{"kind":"arxiv","id":"2410.09375","version":2},"attestation_state":"computed","paper":{"title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CC"],"primary_cat":"cs.LG","authors_text":"Yingyu Liang, Yufa Zhou, Zhao Song, Zhenmei Shi, Zhizhou Sha","submitted_at":"2024-10-12T05:54:17Z","abstract_excerpt":"Previous work has demonstrated that attention mechanisms are Turing complete. More recently, it has been shown that a looped 9-layer Transformer can function as a universal programmable computer. In contrast, the multi-layer perceptrons with $\\mathsf{ReLU}$ activation ($\\mathsf{ReLU}$-$\\mathsf{MLP}$), one of the most fundamental components of neural networks, is known to be expressive; specifically, a two-layer neural network is a universal approximator given an exponentially large number of hidden neurons. However, it remains unclear whether a $\\mathsf{ReLU}$-$\\mathsf{MLP}$ can be made into a"},"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":"2410.09375","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T05:54:17Z","cross_cats_sorted":["cs.AI","cs.CC"],"title_canon_sha256":"b3dffdcbaa1aaeddf79f9ec1385e72082940c9834da1700b8f2643af37e6f54c","abstract_canon_sha256":"55fa27ca2beb85c71731e91a47b03e6c17d513130660f0cf4cb000c29c431422"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:12.120887Z","signature_b64":"+f53YG1TfhS83uGD42ydWkA+IhBFqOUX8hhy8KQ4A3wU4r7/JM3qGGXNLWzy/j+8eayfYA59NDmfMULdWH1rCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6e3b1bd59f8a6987a9b1bf03c19d9ca252f6e1f3fabb37d4bd47de7c3ff0486","last_reissued_at":"2026-07-05T10:17:12.120380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:12.120380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CC"],"primary_cat":"cs.LG","authors_text":"Yingyu Liang, Yufa Zhou, Zhao Song, Zhenmei Shi, Zhizhou Sha","submitted_at":"2024-10-12T05:54:17Z","abstract_excerpt":"Previous work has demonstrated that attention mechanisms are Turing complete. More recently, it has been shown that a looped 9-layer Transformer can function as a universal programmable computer. In contrast, the multi-layer perceptrons with $\\mathsf{ReLU}$ activation ($\\mathsf{ReLU}$-$\\mathsf{MLP}$), one of the most fundamental components of neural networks, is known to be expressive; specifically, a two-layer neural network is a universal approximator given an exponentially large number of hidden neurons. However, it remains unclear whether a $\\mathsf{ReLU}$-$\\mathsf{MLP}$ can be made into a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09375","kind":"arxiv","version":2},"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/2410.09375/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":"2410.09375","created_at":"2026-07-05T10:17:12.120440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09375v2","created_at":"2026-07-05T10:17:12.120440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09375","created_at":"2026-07-05T10:17:12.120440+00:00"},{"alias_kind":"pith_short_12","alias_value":"43R3DPKZ7CTJ","created_at":"2026-07-05T10:17:12.120440+00:00"},{"alias_kind":"pith_short_16","alias_value":"43R3DPKZ7CTJQ6U3","created_at":"2026-07-05T10:17:12.120440+00:00"},{"alias_kind":"pith_short_8","alias_value":"43R3DPKZ","created_at":"2026-07-05T10:17:12.120440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08150","citing_title":"Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI","json":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI.json","graph_json":"https://pith.science/api/pith-number/43R3DPKZ7CTJQ6U3DPYDYGOZZI/graph.json","events_json":"https://pith.science/api/pith-number/43R3DPKZ7CTJQ6U3DPYDYGOZZI/events.json","paper":"https://pith.science/paper/43R3DPKZ"},"agent_actions":{"view_html":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI","download_json":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI.json","view_paper":"https://pith.science/paper/43R3DPKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09375&json=true","fetch_graph":"https://pith.science/api/pith-number/43R3DPKZ7CTJQ6U3DPYDYGOZZI/graph.json","fetch_events":"https://pith.science/api/pith-number/43R3DPKZ7CTJQ6U3DPYDYGOZZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI/action/storage_attestation","attest_author":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI/action/author_attestation","sign_citation":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI/action/citation_signature","submit_replication":"https://pith.science/pith/43R3DPKZ7CTJQ6U3DPYDYGOZZI/action/replication_record"}},"created_at":"2026-07-05T10:17:12.120440+00:00","updated_at":"2026-07-05T10:17:12.120440+00:00"}