{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LTVRAKBX4FO4JEME5CRSDVCCGK","short_pith_number":"pith:LTVRAKBX","schema_version":"1.0","canonical_sha256":"5ceb102837e15dc49184e8a321d44232b321d0440930d2923dfc05211ddd68a8","source":{"kind":"arxiv","id":"2506.14386","version":1},"attestation_state":"computed","paper":{"title":"ResNets Are Deeper Than You Think","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christian H.X. Ali Mehmeti-G\\\"opel, Michael Wand","submitted_at":"2025-06-17T10:33:22Z","abstract_excerpt":"Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction. Their widespread adoption is often credited to their dramatically improved trainability: residual networks train faster, more stably, and achieve higher accuracy than their feedforward counterparts. While numerous techniques, ranging from improved initialization to advanced learning rate schedules, have been proposed to close the performance gap between residual and feedforward networks, this gap has persisted. In this work, we propose an alternative explanation: residual net"},"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":"2506.14386","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T10:33:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c354861315f0e8670556b1766637fabd21fa00a2e8502cbcb592f263201f5dd","abstract_canon_sha256":"75068394bbb00191e18645efba54d3c8c433942a2b82c7c1a79bd410ae99c7e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:54.659271Z","signature_b64":"5IC5DS/zIsWFczoi9FkgW5K3pNe53JMEKV7YEoudAyHpjB1rg9Hi3OP7ESUBDRKFOOtM7s0b4A8+/zOulu9XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ceb102837e15dc49184e8a321d44232b321d0440930d2923dfc05211ddd68a8","last_reissued_at":"2026-07-05T11:22:54.658781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:54.658781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResNets Are Deeper Than You Think","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christian H.X. Ali Mehmeti-G\\\"opel, Michael Wand","submitted_at":"2025-06-17T10:33:22Z","abstract_excerpt":"Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction. Their widespread adoption is often credited to their dramatically improved trainability: residual networks train faster, more stably, and achieve higher accuracy than their feedforward counterparts. While numerous techniques, ranging from improved initialization to advanced learning rate schedules, have been proposed to close the performance gap between residual and feedforward networks, this gap has persisted. In this work, we propose an alternative explanation: residual net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14386","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/2506.14386/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":"2506.14386","created_at":"2026-07-05T11:22:54.658842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14386v1","created_at":"2026-07-05T11:22:54.658842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14386","created_at":"2026-07-05T11:22:54.658842+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTVRAKBX4FO4","created_at":"2026-07-05T11:22:54.658842+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTVRAKBX4FO4JEME","created_at":"2026-07-05T11:22:54.658842+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTVRAKBX","created_at":"2026-07-05T11:22:54.658842+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05866","citing_title":"Differentially Private Natural Gradient Descent","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK","json":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK.json","graph_json":"https://pith.science/api/pith-number/LTVRAKBX4FO4JEME5CRSDVCCGK/graph.json","events_json":"https://pith.science/api/pith-number/LTVRAKBX4FO4JEME5CRSDVCCGK/events.json","paper":"https://pith.science/paper/LTVRAKBX"},"agent_actions":{"view_html":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK","download_json":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK.json","view_paper":"https://pith.science/paper/LTVRAKBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14386&json=true","fetch_graph":"https://pith.science/api/pith-number/LTVRAKBX4FO4JEME5CRSDVCCGK/graph.json","fetch_events":"https://pith.science/api/pith-number/LTVRAKBX4FO4JEME5CRSDVCCGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK/action/storage_attestation","attest_author":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK/action/author_attestation","sign_citation":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK/action/citation_signature","submit_replication":"https://pith.science/pith/LTVRAKBX4FO4JEME5CRSDVCCGK/action/replication_record"}},"created_at":"2026-07-05T11:22:54.658842+00:00","updated_at":"2026-07-05T11:22:54.658842+00:00"}