{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IG2E7DV7KLMRLILL2RX6VREG74","short_pith_number":"pith:IG2E7DV7","schema_version":"1.0","canonical_sha256":"41b44f8ebf52d915a16bd46feac486ff023faac754021cb347c667dee2c9e6f7","source":{"kind":"arxiv","id":"2505.22074","version":1},"attestation_state":"computed","paper":{"title":"The Resurrection of the ReLU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernhard A. Moser, Christoph Linse, Co\\c{s}ku Can Horuz, Geoffrey Kasenbacher, Jendrik Stoltz, Moritz Pesl, Saya Higuchi, Sebastian Kairat, Sebastian Otte, Thomas Martinetz","submitted_at":"2025-05-28T07:55:51Z","abstract_excerpt":"Modeling sophisticated activation functions within deep learning architectures has evolved into a distinct research direction. Functions such as GELU, SELU, and SiLU offer smooth gradients and improved convergence properties, making them popular choices in state-of-the-art models. Despite this trend, the classical ReLU remains appealing due to its simplicity, inherent sparsity, and other advantageous topological characteristics. However, ReLU units are prone to becoming irreversibly inactive - a phenomenon known as the dying ReLU problem - which limits their overall effectiveness. In this work"},"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":"2505.22074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T07:55:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ade1188e66f66a09e19a0684ff3215b96af3a4e7395a338334f5a8dc1d38cbb6","abstract_canon_sha256":"ff018116283ec21d6ef635537fd5b85a03c694bedfe45f361de7b3b24e6dd1d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:09.400742Z","signature_b64":"9erZYvW6l7dpkcbSKPU8AmTpz656eip0V5joOveNAA9aVRzCj4DZK0NQiE2yo80EqtUC5n1uvCCyQOFG6F03DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41b44f8ebf52d915a16bd46feac486ff023faac754021cb347c667dee2c9e6f7","last_reissued_at":"2026-07-05T11:11:09.400180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:09.400180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Resurrection of the ReLU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernhard A. Moser, Christoph Linse, Co\\c{s}ku Can Horuz, Geoffrey Kasenbacher, Jendrik Stoltz, Moritz Pesl, Saya Higuchi, Sebastian Kairat, Sebastian Otte, Thomas Martinetz","submitted_at":"2025-05-28T07:55:51Z","abstract_excerpt":"Modeling sophisticated activation functions within deep learning architectures has evolved into a distinct research direction. Functions such as GELU, SELU, and SiLU offer smooth gradients and improved convergence properties, making them popular choices in state-of-the-art models. Despite this trend, the classical ReLU remains appealing due to its simplicity, inherent sparsity, and other advantageous topological characteristics. However, ReLU units are prone to becoming irreversibly inactive - a phenomenon known as the dying ReLU problem - which limits their overall effectiveness. In this work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22074","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/2505.22074/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":"2505.22074","created_at":"2026-07-05T11:11:09.400241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22074v1","created_at":"2026-07-05T11:11:09.400241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22074","created_at":"2026-07-05T11:11:09.400241+00:00"},{"alias_kind":"pith_short_12","alias_value":"IG2E7DV7KLMR","created_at":"2026-07-05T11:11:09.400241+00:00"},{"alias_kind":"pith_short_16","alias_value":"IG2E7DV7KLMRLILL","created_at":"2026-07-05T11:11:09.400241+00:00"},{"alias_kind":"pith_short_8","alias_value":"IG2E7DV7","created_at":"2026-07-05T11:11:09.400241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17659","citing_title":"Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17659","citing_title":"Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74","json":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74.json","graph_json":"https://pith.science/api/pith-number/IG2E7DV7KLMRLILL2RX6VREG74/graph.json","events_json":"https://pith.science/api/pith-number/IG2E7DV7KLMRLILL2RX6VREG74/events.json","paper":"https://pith.science/paper/IG2E7DV7"},"agent_actions":{"view_html":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74","download_json":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74.json","view_paper":"https://pith.science/paper/IG2E7DV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22074&json=true","fetch_graph":"https://pith.science/api/pith-number/IG2E7DV7KLMRLILL2RX6VREG74/graph.json","fetch_events":"https://pith.science/api/pith-number/IG2E7DV7KLMRLILL2RX6VREG74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74/action/storage_attestation","attest_author":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74/action/author_attestation","sign_citation":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74/action/citation_signature","submit_replication":"https://pith.science/pith/IG2E7DV7KLMRLILL2RX6VREG74/action/replication_record"}},"created_at":"2026-07-05T11:11:09.400241+00:00","updated_at":"2026-07-05T11:11:09.400241+00:00"}