{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZKTXUE4YIDKPFI5PT4G7Z6EZ6K","short_pith_number":"pith:ZKTXUE4Y","canonical_record":{"source":{"id":"1808.07390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2018-08-22T14:45:46Z","cross_cats_sorted":["cs.LG","cs.NA","cs.NE"],"title_canon_sha256":"31b483cb7e72d9da5049a91ae3d9e892ddf296bf5829d9e0019ba65fb09a8499","abstract_canon_sha256":"90cb3565fc2b1ed1f599b7c35721ea90e7e02f76d80199b28f4ba495e1eee5b3"},"schema_version":"1.0"},"canonical_sha256":"caa77a139840d4f2a3af9f0dfcf899f29fc34b4d96c26b91c04f5d42f4e1ccbb","source":{"kind":"arxiv","id":"1808.07390","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07390","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07390v1","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07390","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZKTXUE4YIDKP","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZKTXUE4YIDKPFI5P","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZKTXUE4Y","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZKTXUE4YIDKPFI5PT4G7Z6EZ6K","target":"record","payload":{"canonical_record":{"source":{"id":"1808.07390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2018-08-22T14:45:46Z","cross_cats_sorted":["cs.LG","cs.NA","cs.NE"],"title_canon_sha256":"31b483cb7e72d9da5049a91ae3d9e892ddf296bf5829d9e0019ba65fb09a8499","abstract_canon_sha256":"90cb3565fc2b1ed1f599b7c35721ea90e7e02f76d80199b28f4ba495e1eee5b3"},"schema_version":"1.0"},"canonical_sha256":"caa77a139840d4f2a3af9f0dfcf899f29fc34b4d96c26b91c04f5d42f4e1ccbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:29.000430Z","signature_b64":"W9Lzm/G5qKUt+LRfHXPa6GHX6S+a738W10ni6nM/meYaWoZuaPrkhAZgDh6JgEWvkJYUeWsfYpXh8xa3czVZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa77a139840d4f2a3af9f0dfcf899f29fc34b4d96c26b91c04f5d42f4e1ccbb","last_reissued_at":"2026-05-18T00:07:28.999861Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:28.999861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.07390","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGR26jhHtexwigShPku5roBdk/renQ8S+N7n4cv/WTtPtSxP2dGNXMtELO/LtNOQVc1DrAOFJE+TH8DqNmlSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:03:36.129073Z"},"content_sha256":"791cb442b8d72cfbe9d9022e26971bd5805bd87d557778ec77379008ceae9b22","schema_version":"1.0","event_id":"sha256:791cb442b8d72cfbe9d9022e26971bd5805bd87d557778ec77379008ceae9b22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZKTXUE4YIDKPFI5PT4G7Z6EZ6K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Explicit Neural Network Construction for Piecewise Constant Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","cs.NE"],"primary_cat":"math.NA","authors_text":"Dongbin Xiu, Kailiang Wu","submitted_at":"2018-08-22T14:45:46Z","abstract_excerpt":"We present an explicit construction for feedforward neural network (FNN), which provides a piecewise constant approximation for multivariate functions. The proposed FNN has two hidden layers, where the weights and thresholds are explicitly defined and do not require numerical optimization for training. Unlike most of the existing work on explicit FNN construction, the proposed FNN does not rely on tensor structure in multiple dimensions. Instead, it automatically creates Voronoi tessellation of the domain, based on the given data of the target function, and piecewise constant approximation of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07390","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LR1h+gUvqrKLR393rXghImL94N7K5ZfCoHZwRgWI/T+xBHeajDDa+42ezpUduVL3GLrQ5nsunVNH+Zx7DRYQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:03:36.129473Z"},"content_sha256":"ca12e31df915cf46a8b742bce4f44f64c6b62005316930c63a401250615d0182","schema_version":"1.0","event_id":"sha256:ca12e31df915cf46a8b742bce4f44f64c6b62005316930c63a401250615d0182"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKTXUE4YIDKPFI5PT4G7Z6EZ6K/bundle.json","state_url":"https://pith.science/pith/ZKTXUE4YIDKPFI5PT4G7Z6EZ6K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKTXUE4YIDKPFI5PT4G7Z6EZ6K/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T01:03:36Z","links":{"resolver":"https://pith.science/pith/ZKTXUE4YIDKPFI5PT4G7Z6EZ6K","bundle":"https://pith.science/pith/ZKTXUE4YIDKPFI5PT4G7Z6EZ6K/bundle.json","state":"https://pith.science/pith/ZKTXUE4YIDKPFI5PT4G7Z6EZ6K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKTXUE4YIDKPFI5PT4G7Z6EZ6K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZKTXUE4YIDKPFI5PT4G7Z6EZ6K","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":"90cb3565fc2b1ed1f599b7c35721ea90e7e02f76d80199b28f4ba495e1eee5b3","cross_cats_sorted":["cs.LG","cs.NA","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2018-08-22T14:45:46Z","title_canon_sha256":"31b483cb7e72d9da5049a91ae3d9e892ddf296bf5829d9e0019ba65fb09a8499"},"schema_version":"1.0","source":{"id":"1808.07390","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07390","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07390v1","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07390","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZKTXUE4YIDKP","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZKTXUE4YIDKPFI5P","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZKTXUE4Y","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:ca12e31df915cf46a8b742bce4f44f64c6b62005316930c63a401250615d0182","target":"graph","created_at":"2026-05-18T00:07:28Z","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"},"paper":{"abstract_excerpt":"We present an explicit construction for feedforward neural network (FNN), which provides a piecewise constant approximation for multivariate functions. The proposed FNN has two hidden layers, where the weights and thresholds are explicitly defined and do not require numerical optimization for training. Unlike most of the existing work on explicit FNN construction, the proposed FNN does not rely on tensor structure in multiple dimensions. Instead, it automatically creates Voronoi tessellation of the domain, based on the given data of the target function, and piecewise constant approximation of ","authors_text":"Dongbin Xiu, Kailiang Wu","cross_cats":["cs.LG","cs.NA","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2018-08-22T14:45:46Z","title":"An Explicit Neural Network Construction for Piecewise Constant Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07390","kind":"arxiv","version":1},"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":"sha256:791cb442b8d72cfbe9d9022e26971bd5805bd87d557778ec77379008ceae9b22","target":"record","created_at":"2026-05-18T00:07:28Z","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":"90cb3565fc2b1ed1f599b7c35721ea90e7e02f76d80199b28f4ba495e1eee5b3","cross_cats_sorted":["cs.LG","cs.NA","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2018-08-22T14:45:46Z","title_canon_sha256":"31b483cb7e72d9da5049a91ae3d9e892ddf296bf5829d9e0019ba65fb09a8499"},"schema_version":"1.0","source":{"id":"1808.07390","kind":"arxiv","version":1}},"canonical_sha256":"caa77a139840d4f2a3af9f0dfcf899f29fc34b4d96c26b91c04f5d42f4e1ccbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caa77a139840d4f2a3af9f0dfcf899f29fc34b4d96c26b91c04f5d42f4e1ccbb","first_computed_at":"2026-05-18T00:07:28.999861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:28.999861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W9Lzm/G5qKUt+LRfHXPa6GHX6S+a738W10ni6nM/meYaWoZuaPrkhAZgDh6JgEWvkJYUeWsfYpXh8xa3czVZDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:29.000430Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.07390","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:791cb442b8d72cfbe9d9022e26971bd5805bd87d557778ec77379008ceae9b22","sha256:ca12e31df915cf46a8b742bce4f44f64c6b62005316930c63a401250615d0182"],"state_sha256":"258ed30ca1920d436db68e9f9fd83f177016ef5864369ccfa3365fd0b4e93454"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R01wJT5oAfpty+drh7087x6SpCtjSNbVm/2rk88RfORxLnvB3wbGONcn1sp3EIu7kVyoJUMe1hzyV6Qv9p1NDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T01:03:36.131610Z","bundle_sha256":"ce4b83f9775f4effa5c32ca26a7e52a55fac36f319801961c4e47072858e858a"}}