{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MH3E5KLVJ5H2TPL6BKXIHAJIES","short_pith_number":"pith:MH3E5KLV","schema_version":"1.0","canonical_sha256":"61f64ea9754f4fa9bd7e0aae83812824a959168210fe144fdc63e8ebca82f371","source":{"kind":"arxiv","id":"2507.06148","version":1},"attestation_state":"computed","paper":{"title":"SoftReMish: A Novel Activation Function for Enhanced Convolutional Neural Networks for Visual Recognition Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CV","authors_text":"Mustafa Bayram G\\\"ucen","submitted_at":"2025-07-08T16:29:14Z","abstract_excerpt":"In this study, SoftReMish, a new activation function designed to improve the performance of convolutional neural networks (CNNs) in image classification tasks, is proposed. Using the MNIST dataset, a standard CNN architecture consisting of two convolutional layers, max pooling, and fully connected layers was implemented. SoftReMish was evaluated against popular activation functions including ReLU, Tanh, and Mish by replacing the activation function in all trainable layers. The model performance was assessed in terms of minimum training loss and maximum validation accuracy. Results showed that "},"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":"2507.06148","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T16:29:14Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"e3548537f74760373ebdfec0020521439e5a21bf917ab9e1255a038794164c1f","abstract_canon_sha256":"9fe3b667fe84166c1fc352b7b434b55be75d213b7a3c310473757894649f4167"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:52.821736Z","signature_b64":"/HOWm7RhPUkpfwT+U4NDWb4uBCqfMe0x6r+ujjp15MClrw0GLdHraPluhphJQ7ghGk0XSawlouS3Yel7pOGeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61f64ea9754f4fa9bd7e0aae83812824a959168210fe144fdc63e8ebca82f371","last_reissued_at":"2026-07-05T11:33:52.821259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:52.821259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoftReMish: A Novel Activation Function for Enhanced Convolutional Neural Networks for Visual Recognition Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CV","authors_text":"Mustafa Bayram G\\\"ucen","submitted_at":"2025-07-08T16:29:14Z","abstract_excerpt":"In this study, SoftReMish, a new activation function designed to improve the performance of convolutional neural networks (CNNs) in image classification tasks, is proposed. Using the MNIST dataset, a standard CNN architecture consisting of two convolutional layers, max pooling, and fully connected layers was implemented. SoftReMish was evaluated against popular activation functions including ReLU, Tanh, and Mish by replacing the activation function in all trainable layers. The model performance was assessed in terms of minimum training loss and maximum validation accuracy. Results showed that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06148","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/2507.06148/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":"2507.06148","created_at":"2026-07-05T11:33:52.821324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06148v1","created_at":"2026-07-05T11:33:52.821324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06148","created_at":"2026-07-05T11:33:52.821324+00:00"},{"alias_kind":"pith_short_12","alias_value":"MH3E5KLVJ5H2","created_at":"2026-07-05T11:33:52.821324+00:00"},{"alias_kind":"pith_short_16","alias_value":"MH3E5KLVJ5H2TPL6","created_at":"2026-07-05T11:33:52.821324+00:00"},{"alias_kind":"pith_short_8","alias_value":"MH3E5KLV","created_at":"2026-07-05T11:33:52.821324+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/MH3E5KLVJ5H2TPL6BKXIHAJIES","json":"https://pith.science/pith/MH3E5KLVJ5H2TPL6BKXIHAJIES.json","graph_json":"https://pith.science/api/pith-number/MH3E5KLVJ5H2TPL6BKXIHAJIES/graph.json","events_json":"https://pith.science/api/pith-number/MH3E5KLVJ5H2TPL6BKXIHAJIES/events.json","paper":"https://pith.science/paper/MH3E5KLV"},"agent_actions":{"view_html":"https://pith.science/pith/MH3E5KLVJ5H2TPL6BKXIHAJIES","download_json":"https://pith.science/pith/MH3E5KLVJ5H2TPL6BKXIHAJIES.json","view_paper":"https://pith.science/paper/MH3E5KLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06148&json=true","fetch_graph":"https://pith.science/api/pith-number/MH3E5KLVJ5H2TPL6BKXIHAJIES/graph.json","fetch_events":"https://pith.science/api/pith-number/MH3E5KLVJ5H2TPL6BKXIHAJIES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MH3E5KLVJ5H2TPL6BKXIHAJIES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MH3E5KLVJ5H2TPL6BKXIHAJIES/action/storage_attestation","attest_author":"https://pith.science/pith/MH3E5KLVJ5H2TPL6BKXIHAJIES/action/author_attestation","sign_citation":"https://pith.science/pith/MH3E5KLVJ5H2TPL6BKXIHAJIES/action/citation_signature","submit_replication":"https://pith.science/pith/MH3E5KLVJ5H2TPL6BKXIHAJIES/action/replication_record"}},"created_at":"2026-07-05T11:33:52.821324+00:00","updated_at":"2026-07-05T11:33:52.821324+00:00"}