{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BEEPY2BXOZV3CY4QNCYLXSCXON","short_pith_number":"pith:BEEPY2BX","schema_version":"1.0","canonical_sha256":"0908fc6837766bb1639068b0bbc857734d1b496be7378e6745b9747b1f366145","source":{"kind":"arxiv","id":"2510.22450","version":3},"attestation_state":"computed","paper":{"title":"SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amin Omidvar","submitted_at":"2025-10-25T22:46:37Z","abstract_excerpt":"The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons. We introduce SmartMixed, a novel two-phase training strategy that allows networks to learn optimal per-neuron activation functions while preserving computational efficiency at inference. In the first phase, neurons adaptively select from a pool of candidate activation functions (ReLU, Sigmoid, Tanh, Leaky\\_ReLU, ELU, SELU) using a differentiable hard mixture mechanism. In the second phase, each neuron's activation function is f"},"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":"2510.22450","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-25T22:46:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"05f93e7cc2f95b6dfee50642e8a32e76ad8ddcba242e7810172daaa431d878a6","abstract_canon_sha256":"3efff74101de9a7cc496051ebf4cad496c8264e5a9b9e5cb8cdfbb7eb44abb82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:10.135321Z","signature_b64":"oue//RYXdU3ehDyCmh3Tx0nWckuymXrNuuzuL1kUaYU2mgvp1a/PKKWD/0SpWJfUijAN74tOY3USyBUvVF5PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0908fc6837766bb1639068b0bbc857734d1b496be7378e6745b9747b1f366145","last_reissued_at":"2026-06-09T01:05:10.134743Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:10.134743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amin Omidvar","submitted_at":"2025-10-25T22:46:37Z","abstract_excerpt":"The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons. We introduce SmartMixed, a novel two-phase training strategy that allows networks to learn optimal per-neuron activation functions while preserving computational efficiency at inference. In the first phase, neurons adaptively select from a pool of candidate activation functions (ReLU, Sigmoid, Tanh, Leaky\\_ReLU, ELU, SELU) using a differentiable hard mixture mechanism. In the second phase, each neuron's activation function is f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.22450","kind":"arxiv","version":3},"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/2510.22450/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":"2510.22450","created_at":"2026-06-09T01:05:10.134819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.22450v3","created_at":"2026-06-09T01:05:10.134819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.22450","created_at":"2026-06-09T01:05:10.134819+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEEPY2BXOZV3","created_at":"2026-06-09T01:05:10.134819+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEEPY2BXOZV3CY4Q","created_at":"2026-06-09T01:05:10.134819+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEEPY2BX","created_at":"2026-06-09T01:05:10.134819+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/BEEPY2BXOZV3CY4QNCYLXSCXON","json":"https://pith.science/pith/BEEPY2BXOZV3CY4QNCYLXSCXON.json","graph_json":"https://pith.science/api/pith-number/BEEPY2BXOZV3CY4QNCYLXSCXON/graph.json","events_json":"https://pith.science/api/pith-number/BEEPY2BXOZV3CY4QNCYLXSCXON/events.json","paper":"https://pith.science/paper/BEEPY2BX"},"agent_actions":{"view_html":"https://pith.science/pith/BEEPY2BXOZV3CY4QNCYLXSCXON","download_json":"https://pith.science/pith/BEEPY2BXOZV3CY4QNCYLXSCXON.json","view_paper":"https://pith.science/paper/BEEPY2BX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.22450&json=true","fetch_graph":"https://pith.science/api/pith-number/BEEPY2BXOZV3CY4QNCYLXSCXON/graph.json","fetch_events":"https://pith.science/api/pith-number/BEEPY2BXOZV3CY4QNCYLXSCXON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEEPY2BXOZV3CY4QNCYLXSCXON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEEPY2BXOZV3CY4QNCYLXSCXON/action/storage_attestation","attest_author":"https://pith.science/pith/BEEPY2BXOZV3CY4QNCYLXSCXON/action/author_attestation","sign_citation":"https://pith.science/pith/BEEPY2BXOZV3CY4QNCYLXSCXON/action/citation_signature","submit_replication":"https://pith.science/pith/BEEPY2BXOZV3CY4QNCYLXSCXON/action/replication_record"}},"created_at":"2026-06-09T01:05:10.134819+00:00","updated_at":"2026-06-09T01:05:10.134819+00:00"}