{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RUPUJQQ3Y3JLCFZ5BF6P4B2T5A","short_pith_number":"pith:RUPUJQQ3","schema_version":"1.0","canonical_sha256":"8d1f44c21bc6d2b1173d097cfe0753e812e94dd04621ad61f5d9b998596b3428","source":{"kind":"arxiv","id":"2006.13858","version":2},"attestation_state":"computed","paper":{"title":"AReLU: Attention-based Rectified Linear Unit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dengsheng Chen, Jun Li, Kai Xu","submitted_at":"2020-06-24T16:39:16Z","abstract_excerpt":"Element-wise activation functions play a critical role in deep neural networks via affecting the expressivity power and the learning dynamics. Learning-based activation functions have recently gained increasing attention and success. We propose a new perspective of learnable activation function through formulating them with element-wise attention mechanism. In each network layer, we devise an attention module which learns an element-wise, sign-based attention map for the pre-activation feature map. The attention map scales an element based on its sign. Adding the attention module with a rectif"},"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":"2006.13858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T16:39:16Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"09803dd5393b86a2da6a938f78a1e3c142e5b4ffd03450899bf7c9380dee0831","abstract_canon_sha256":"109f58b813356f5d87d86db54bd974c58a0eefa48346a26effccdf350d9a7982"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:44.104011Z","signature_b64":"Mu4s7tc1P5G8AgkTEZNdQSW01rBsFYeosMoOGaDKvKlhdJjG5PPWqqInZmuky+IaKhRWhYwDyPb8YEIsQLgACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d1f44c21bc6d2b1173d097cfe0753e812e94dd04621ad61f5d9b998596b3428","last_reissued_at":"2026-07-05T01:39:44.103488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:44.103488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AReLU: Attention-based Rectified Linear Unit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dengsheng Chen, Jun Li, Kai Xu","submitted_at":"2020-06-24T16:39:16Z","abstract_excerpt":"Element-wise activation functions play a critical role in deep neural networks via affecting the expressivity power and the learning dynamics. Learning-based activation functions have recently gained increasing attention and success. We propose a new perspective of learnable activation function through formulating them with element-wise attention mechanism. In each network layer, we devise an attention module which learns an element-wise, sign-based attention map for the pre-activation feature map. The attention map scales an element based on its sign. Adding the attention module with a rectif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13858","kind":"arxiv","version":2},"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/2006.13858/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":"2006.13858","created_at":"2026-07-05T01:39:44.103552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.13858v2","created_at":"2026-07-05T01:39:44.103552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13858","created_at":"2026-07-05T01:39:44.103552+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUPUJQQ3Y3JL","created_at":"2026-07-05T01:39:44.103552+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUPUJQQ3Y3JLCFZ5","created_at":"2026-07-05T01:39:44.103552+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUPUJQQ3","created_at":"2026-07-05T01:39:44.103552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09158","citing_title":"Automatic Contouring of Spinal Vertebrae on X-Ray using a Novel Sandwich U-Net Architecture","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A","json":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A.json","graph_json":"https://pith.science/api/pith-number/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/graph.json","events_json":"https://pith.science/api/pith-number/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/events.json","paper":"https://pith.science/paper/RUPUJQQ3"},"agent_actions":{"view_html":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A","download_json":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A.json","view_paper":"https://pith.science/paper/RUPUJQQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.13858&json=true","fetch_graph":"https://pith.science/api/pith-number/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/graph.json","fetch_events":"https://pith.science/api/pith-number/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/action/storage_attestation","attest_author":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/action/author_attestation","sign_citation":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/action/citation_signature","submit_replication":"https://pith.science/pith/RUPUJQQ3Y3JLCFZ5BF6P4B2T5A/action/replication_record"}},"created_at":"2026-07-05T01:39:44.103552+00:00","updated_at":"2026-07-05T01:39:44.103552+00:00"}