{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PCRIFIFQ3AKX2NASO54YF2G3MG","short_pith_number":"pith:PCRIFIFQ","canonical_record":{"source":{"id":"2602.04264","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T06:55:55Z","cross_cats_sorted":["cs.AI","cs.NA","math.NA"],"title_canon_sha256":"9dca2bdd3ff3db2aeb9324011d1269d146505ca4273ea572b9e32bb75e3657ef","abstract_canon_sha256":"daf496ce8d5fdc03fd988f3cbf5e60d5a7035e082ddce5807565ae7394c802f1"},"schema_version":"1.0"},"canonical_sha256":"78a282a0b0d8157d3412777982e8db619aa4a10971f47739c25c4edf2c67c76a","source":{"kind":"arxiv","id":"2602.04264","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04264","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04264v2","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04264","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"PCRIFIFQ3AKX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PCRIFIFQ3AKX2NAS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PCRIFIFQ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PCRIFIFQ3AKX2NASO54YF2G3MG","target":"record","payload":{"canonical_record":{"source":{"id":"2602.04264","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T06:55:55Z","cross_cats_sorted":["cs.AI","cs.NA","math.NA"],"title_canon_sha256":"9dca2bdd3ff3db2aeb9324011d1269d146505ca4273ea572b9e32bb75e3657ef","abstract_canon_sha256":"daf496ce8d5fdc03fd988f3cbf5e60d5a7035e082ddce5807565ae7394c802f1"},"schema_version":"1.0"},"canonical_sha256":"78a282a0b0d8157d3412777982e8db619aa4a10971f47739c25c4edf2c67c76a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:23.944138Z","signature_b64":"dmoNaeWEfwBlbUZnGUNqcaaEXjn27sURHkBt5Ofht2aYI/+ySBIoqJgR6A2PrJBcAd30GdxaN3B1easovfw0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78a282a0b0d8157d3412777982e8db619aa4a10971f47739c25c4edf2c67c76a","last_reissued_at":"2026-05-18T03:09:23.943437Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:23.943437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.04264","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FRXl8+YEnF3wkTKzdusdeqCtfyULHiMOwxlleDEyVNrhPdD3PX7UQZgDpL4mk2JvPI7Vmhgn+xxyPFI4DlO2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:05:45.777570Z"},"content_sha256":"1fd522757d9b972fcebd55d542dea88b10ccadb86b77273b6f9c881c9b2d82e5","schema_version":"1.0","event_id":"sha256:1fd522757d9b972fcebd55d542dea88b10ccadb86b77273b6f9c881c9b2d82e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PCRIFIFQ3AKX2NASO54YF2G3MG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exponential Approximation Rates and Parameter Efficiency of Learnable Bernstein Activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Learnable Bernstein polynomial activations achieve approximation error decaying as O(n^{-L}) with network depth and polynomial order, exponentially faster than ReLU networks while remaining fully differentiable.","cross_cats":["cs.AI","cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Ibrahim Albool, Malak Gamal El-Din, Salma Elmalaki, Yasser Shoukry","submitted_at":"2026-02-04T06:55:55Z","abstract_excerpt":"The choice of activation function fundamentally shapes the representational capacity and parameter efficiency of deep neural networks, yet most widely used activations lack rigorous theoretical guarantees on these properties. We provide a theoretical analysis of DeepBern-Nets (DBNs) -- networks employing learnable Bernstein polynomial activations -- showing that their approximation error decays with the network depth $L$ and the polynomial order $n$ with a rate of $\\mathcal{O}(n^{-L})$, exponentially faster than the polynomial rate of ReLU architectures while remaining fully differentiable. We"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"their approximation error decays with the network depth L and the polynomial order n with a rate of O(n^{-L}), exponentially faster than the polynomial rate of ReLU architectures while remaining fully differentiable.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The theoretical analysis assumes that the learnable Bernstein activations can be integrated into standard deep network architectures without introducing optimization difficulties that would negate the approximation benefits.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Learnable Bernstein activations achieve exponential approximation rates O(n^{-L}) and deliver up to 99.9% parameter reduction while matching or exceeding ReLU performance on large physics datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Learnable Bernstein polynomial activations achieve approximation error decaying as O(n^{-L}) with network depth and polynomial order, exponentially faster than ReLU networks while remaining fully differentiable.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b19bf706497aeb3914a5b98d0fe5f251ccba65d4ba402c2bc2e855d5d9ede52b"},"source":{"id":"2602.04264","kind":"arxiv","version":2},"verdict":{"id":"835e7e28-f152-40ee-8d83-569bc83ac93e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T07:19:05.531502Z","strongest_claim":"their approximation error decays with the network depth L and the polynomial order n with a rate of O(n^{-L}), exponentially faster than the polynomial rate of ReLU architectures while remaining fully differentiable.","one_line_summary":"Learnable Bernstein activations achieve exponential approximation rates O(n^{-L}) and deliver up to 99.9% parameter reduction while matching or exceeding ReLU performance on large physics datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The theoretical analysis assumes that the learnable Bernstein activations can be integrated into standard deep network architectures without introducing optimization difficulties that would negate the approximation benefits.","pith_extraction_headline":"Learnable Bernstein polynomial activations achieve approximation error decaying as O(n^{-L}) with network depth and polynomial order, exponentially faster than ReLU networks while remaining fully differentiable."},"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":"835e7e28-f152-40ee-8d83-569bc83ac93e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/6//VIENX98HE78Suj9m4t31j5V/XnJgsLUVu3uQGqkSpjG+FzFBlY2FUx3oeMEVXzGHb6OSnREibgtrH65Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:05:45.778192Z"},"content_sha256":"d5f8775ffe79b91956f1c90e865a8d76a1bc01d632a4cd2d62bbed789fb99fe6","schema_version":"1.0","event_id":"sha256:d5f8775ffe79b91956f1c90e865a8d76a1bc01d632a4cd2d62bbed789fb99fe6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCRIFIFQ3AKX2NASO54YF2G3MG/bundle.json","state_url":"https://pith.science/pith/PCRIFIFQ3AKX2NASO54YF2G3MG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCRIFIFQ3AKX2NASO54YF2G3MG/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":"2026-06-08T19:05:45Z","links":{"resolver":"https://pith.science/pith/PCRIFIFQ3AKX2NASO54YF2G3MG","bundle":"https://pith.science/pith/PCRIFIFQ3AKX2NASO54YF2G3MG/bundle.json","state":"https://pith.science/pith/PCRIFIFQ3AKX2NASO54YF2G3MG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCRIFIFQ3AKX2NASO54YF2G3MG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PCRIFIFQ3AKX2NASO54YF2G3MG","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":"daf496ce8d5fdc03fd988f3cbf5e60d5a7035e082ddce5807565ae7394c802f1","cross_cats_sorted":["cs.AI","cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T06:55:55Z","title_canon_sha256":"9dca2bdd3ff3db2aeb9324011d1269d146505ca4273ea572b9e32bb75e3657ef"},"schema_version":"1.0","source":{"id":"2602.04264","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04264","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04264v2","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04264","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"PCRIFIFQ3AKX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PCRIFIFQ3AKX2NAS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PCRIFIFQ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d5f8775ffe79b91956f1c90e865a8d76a1bc01d632a4cd2d62bbed789fb99fe6","target":"graph","created_at":"2026-05-18T03:09:23Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"their approximation error decays with the network depth L and the polynomial order n with a rate of O(n^{-L}), exponentially faster than the polynomial rate of ReLU architectures while remaining fully differentiable."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The theoretical analysis assumes that the learnable Bernstein activations can be integrated into standard deep network architectures without introducing optimization difficulties that would negate the approximation benefits."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Learnable Bernstein activations achieve exponential approximation rates O(n^{-L}) and deliver up to 99.9% parameter reduction while matching or exceeding ReLU performance on large physics datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Learnable Bernstein polynomial activations achieve approximation error decaying as O(n^{-L}) with network depth and polynomial order, exponentially faster than ReLU networks while remaining fully differentiable."}],"snapshot_sha256":"b19bf706497aeb3914a5b98d0fe5f251ccba65d4ba402c2bc2e855d5d9ede52b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The choice of activation function fundamentally shapes the representational capacity and parameter efficiency of deep neural networks, yet most widely used activations lack rigorous theoretical guarantees on these properties. We provide a theoretical analysis of DeepBern-Nets (DBNs) -- networks employing learnable Bernstein polynomial activations -- showing that their approximation error decays with the network depth $L$ and the polynomial order $n$ with a rate of $\\mathcal{O}(n^{-L})$, exponentially faster than the polynomial rate of ReLU architectures while remaining fully differentiable. We","authors_text":"Ibrahim Albool, Malak Gamal El-Din, Salma Elmalaki, Yasser Shoukry","cross_cats":["cs.AI","cs.NA","math.NA"],"headline":"Learnable Bernstein polynomial activations achieve approximation error decaying as O(n^{-L}) with network depth and polynomial order, exponentially faster than ReLU networks while remaining fully differentiable.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T06:55:55Z","title":"Exponential Approximation Rates and Parameter Efficiency of Learnable Bernstein Activations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04264","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T07:19:05.531502Z","id":"835e7e28-f152-40ee-8d83-569bc83ac93e","model_set":{"reader":"grok-4.3"},"one_line_summary":"Learnable Bernstein activations achieve exponential approximation rates O(n^{-L}) and deliver up to 99.9% parameter reduction while matching or exceeding ReLU performance on large physics datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Learnable Bernstein polynomial activations achieve approximation error decaying as O(n^{-L}) with network depth and polynomial order, exponentially faster than ReLU networks while remaining fully differentiable.","strongest_claim":"their approximation error decays with the network depth L and the polynomial order n with a rate of O(n^{-L}), exponentially faster than the polynomial rate of ReLU architectures while remaining fully differentiable.","weakest_assumption":"The theoretical analysis assumes that the learnable Bernstein activations can be integrated into standard deep network architectures without introducing optimization difficulties that would negate the approximation benefits."}},"verdict_id":"835e7e28-f152-40ee-8d83-569bc83ac93e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1fd522757d9b972fcebd55d542dea88b10ccadb86b77273b6f9c881c9b2d82e5","target":"record","created_at":"2026-05-18T03:09:23Z","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":"daf496ce8d5fdc03fd988f3cbf5e60d5a7035e082ddce5807565ae7394c802f1","cross_cats_sorted":["cs.AI","cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T06:55:55Z","title_canon_sha256":"9dca2bdd3ff3db2aeb9324011d1269d146505ca4273ea572b9e32bb75e3657ef"},"schema_version":"1.0","source":{"id":"2602.04264","kind":"arxiv","version":2}},"canonical_sha256":"78a282a0b0d8157d3412777982e8db619aa4a10971f47739c25c4edf2c67c76a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78a282a0b0d8157d3412777982e8db619aa4a10971f47739c25c4edf2c67c76a","first_computed_at":"2026-05-18T03:09:23.943437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:23.943437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dmoNaeWEfwBlbUZnGUNqcaaEXjn27sURHkBt5Ofht2aYI/+ySBIoqJgR6A2PrJBcAd30GdxaN3B1easovfw0AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:23.944138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.04264","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fd522757d9b972fcebd55d542dea88b10ccadb86b77273b6f9c881c9b2d82e5","sha256:d5f8775ffe79b91956f1c90e865a8d76a1bc01d632a4cd2d62bbed789fb99fe6"],"state_sha256":"9d65c5ca9fea9d2593f90d979e2551a15a47fe44927c688bdfbef19c574d51f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"igdguAZFyAGVAVlrNPyJ5Dj6j41WZ/dkkZGi29G5IHDOQstljy7KzpKGulZqmWJ8MaR5EMiCJUz1JzGp8oxYCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T19:05:45.780894Z","bundle_sha256":"2bb0064225b3a72b700d732a2fafdcda557ed24324cf3a10496c0b6650624cb0"}}