{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:47IFXKPMDGEY3ASJN2EZK6F233","short_pith_number":"pith:47IFXKPM","schema_version":"1.0","canonical_sha256":"e7d05ba9ec19898d82496e899578baded2bbd0313cce108dc3a48dcee7bed5fe","source":{"kind":"arxiv","id":"2108.12943","version":3},"attestation_state":"computed","paper":{"title":"Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Advait Trivedi, Arunkumar L, Mathew Mithra Noel, Praneet Dutta","submitted_at":"2021-08-30T01:07:05Z","abstract_excerpt":"Convolutional neural networks have been successful in solving many socially important and economically significant problems. This ability to learn complex high-dimensional functions hierarchically can be attributed to the use of nonlinear activation functions. A key discovery that made training deep networks feasible was the adoption of the Rectified Linear Unit (ReLU) activation function to alleviate the vanishing gradient problem caused by using saturating activation functions. Since then, many improved variants of the ReLU activation have been proposed. However, a majority of activation fun"},"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":"2108.12943","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-30T01:07:05Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"505e66c83f4509644439763f627176034389b1a3003d062d7f592040db5c5221","abstract_canon_sha256":"584ef0604b9621fcd4377ce879dd854babc295cdcdeb343b6ecf68474e3add35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:09.919444Z","signature_b64":"auN7C9dqXmzBQPJVhOF36vwgBKkuFWktjleP67GW0zs/Wc8dGnxbTCQ6Z9u9KAmxKNz2AVxwvmGP8Zw9YJPRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7d05ba9ec19898d82496e899578baded2bbd0313cce108dc3a48dcee7bed5fe","last_reissued_at":"2026-07-05T10:48:09.918934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:09.918934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Advait Trivedi, Arunkumar L, Mathew Mithra Noel, Praneet Dutta","submitted_at":"2021-08-30T01:07:05Z","abstract_excerpt":"Convolutional neural networks have been successful in solving many socially important and economically significant problems. This ability to learn complex high-dimensional functions hierarchically can be attributed to the use of nonlinear activation functions. A key discovery that made training deep networks feasible was the adoption of the Rectified Linear Unit (ReLU) activation function to alleviate the vanishing gradient problem caused by using saturating activation functions. Since then, many improved variants of the ReLU activation have been proposed. However, a majority of activation fun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12943","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/2108.12943/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":"2108.12943","created_at":"2026-07-05T10:48:09.919006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.12943v3","created_at":"2026-07-05T10:48:09.919006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12943","created_at":"2026-07-05T10:48:09.919006+00:00"},{"alias_kind":"pith_short_12","alias_value":"47IFXKPMDGEY","created_at":"2026-07-05T10:48:09.919006+00:00"},{"alias_kind":"pith_short_16","alias_value":"47IFXKPMDGEY3ASJ","created_at":"2026-07-05T10:48:09.919006+00:00"},{"alias_kind":"pith_short_8","alias_value":"47IFXKPM","created_at":"2026-07-05T10:48:09.919006+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/47IFXKPMDGEY3ASJN2EZK6F233","json":"https://pith.science/pith/47IFXKPMDGEY3ASJN2EZK6F233.json","graph_json":"https://pith.science/api/pith-number/47IFXKPMDGEY3ASJN2EZK6F233/graph.json","events_json":"https://pith.science/api/pith-number/47IFXKPMDGEY3ASJN2EZK6F233/events.json","paper":"https://pith.science/paper/47IFXKPM"},"agent_actions":{"view_html":"https://pith.science/pith/47IFXKPMDGEY3ASJN2EZK6F233","download_json":"https://pith.science/pith/47IFXKPMDGEY3ASJN2EZK6F233.json","view_paper":"https://pith.science/paper/47IFXKPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.12943&json=true","fetch_graph":"https://pith.science/api/pith-number/47IFXKPMDGEY3ASJN2EZK6F233/graph.json","fetch_events":"https://pith.science/api/pith-number/47IFXKPMDGEY3ASJN2EZK6F233/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47IFXKPMDGEY3ASJN2EZK6F233/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47IFXKPMDGEY3ASJN2EZK6F233/action/storage_attestation","attest_author":"https://pith.science/pith/47IFXKPMDGEY3ASJN2EZK6F233/action/author_attestation","sign_citation":"https://pith.science/pith/47IFXKPMDGEY3ASJN2EZK6F233/action/citation_signature","submit_replication":"https://pith.science/pith/47IFXKPMDGEY3ASJN2EZK6F233/action/replication_record"}},"created_at":"2026-07-05T10:48:09.919006+00:00","updated_at":"2026-07-05T10:48:09.919006+00:00"}