{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PCFYDLTODMVFSOODEHBMBTOTEX","short_pith_number":"pith:PCFYDLTO","schema_version":"1.0","canonical_sha256":"788b81ae6e1b2a5939c321c2c0cdd325f377d0fb5a3193bb81fa6d3c44768a05","source":{"kind":"arxiv","id":"1512.03385","version":1},"attestation_state":"computed","paper":{"title":"Deep Residual Learning for Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Residual networks reformulate layers to learn differences from inputs via identity shortcuts, making much deeper training feasible and more accurate.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Kaiming He, Shaoqing Ren, Xiangyu Zhang","submitted_at":"2015-12-10T19:51:55Z","abstract_excerpt":"Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG ne"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"1512.03385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-10T19:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"697404a43beb20f7fff7d7cad129017d947ddc3f622768c25861d5bcd9ae9177","abstract_canon_sha256":"1f2b0fe81acdf1248d06a39083d33225c849991d2be531bec10a0aaeb22a755c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T20:43:20.476278Z","signature_b64":"gVNx4hN0KMsHjs0VJwB7nRsXJgqM8nEu/Ekq3p7cLs4wwPKgM0f/hLR47/UfuzaVDEO+6WFqLksA6cu3OugbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"788b81ae6e1b2a5939c321c2c0cdd325f377d0fb5a3193bb81fa6d3c44768a05","last_reissued_at":"2026-07-04T20:43:20.475735Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T20:43:20.475735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Residual Learning for Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Residual networks reformulate layers to learn differences from inputs via identity shortcuts, making much deeper training feasible and more accurate.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Kaiming He, Shaoqing Ren, Xiangyu Zhang","submitted_at":"2015-12-10T19:51:55Z","abstract_excerpt":"Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG ne"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the residual functions with identity shortcuts are substantially easier to optimize than the original unreferenced mappings, which the paper supports through experiments but does not prove theoretically.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Residual networks reformulate layers to learn residual functions, enabling effective training of up to 152-layer models that achieve 3.57% error on ImageNet and win ILSVRC 2015.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Residual networks reformulate layers to learn differences from inputs via identity shortcuts, making much deeper training feasible and more accurate.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4ec60011fc0848f655f86be88bbf37ee9730aa80baf90b84029d6a2adac9eb75"},"source":{"id":"1512.03385","kind":"arxiv","version":1},"verdict":{"id":"b5b5bde3-3086-49e2-bb48-80c26a728df5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T02:57:14.123676Z","strongest_claim":"We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.","one_line_summary":"Residual networks reformulate layers to learn residual functions, enabling effective training of up to 152-layer models that achieve 3.57% error on ImageNet and win ILSVRC 2015.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the residual functions with identity shortcuts are substantially easier to optimize than the original unreferenced mappings, which the paper supports through experiments but does not prove theoretically.","pith_extraction_headline":"Residual networks reformulate layers to learn differences from inputs via identity shortcuts, making much deeper training feasible and more accurate."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1512.03385/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":52,"sample":[{"doi":"","year":1994,"title":"Y . Bengio, P. Simard, and P. Frasconi. Learning long-term dependen- cies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2):157–166, 1994","work_id":"ca85b4a5-7872-4990-849d-ebde6e745221","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1995,"title":"C. M. Bishop. Neural networks for pattern recognition . Oxford university press, 1995","work_id":"ccefb76f-c5b6-49db-800c-d51470b60ef5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2000,"title":"W. L. Briggs, S. F. McCormick, et al. A Multigrid Tutorial. Siam, 2000","work_id":"9e910073-1ded-41c6-b232-24989857a9c7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"K. Chatfield, V . Lempitsky, A. Vedaldi, and A. Zisserman. The devil is in the details: an evaluation of recent feature encoding methods. In BMVC, 2011","work_id":"5adc8414-5588-4c6c-913f-d9dad9367418","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zis- serman. The Pascal Visual Object Classes (VOC) Challenge. IJCV, pages 303–338, 2010","work_id":"c305d929-5eba-44a5-9dd3-a91930dc5833","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":52,"snapshot_sha256":"0a75757926205bcf3ce280378fdb8f65cc601a2d81cb2098ea01ff6c76aed457","internal_anchors":1},"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":"1512.03385","created_at":"2026-07-04T20:43:20.475795+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.03385v1","created_at":"2026-07-04T20:43:20.475795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.03385","created_at":"2026-07-04T20:43:20.475795+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCFYDLTODMVF","created_at":"2026-07-04T20:43:20.475795+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCFYDLTODMVFSOOD","created_at":"2026-07-04T20:43:20.475795+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCFYDLTO","created_at":"2026-07-04T20:43:20.475795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":214,"internal_anchor_count":214,"sample":[{"citing_arxiv_id":"2606.25610","citing_title":"The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26204","citing_title":"Topology-Informed Neural Networks for Flood Detection in Optical and Synthetic Aperture Radar Imagery","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23353","citing_title":"Ultra-Peripheral Collisions as a Nuclear-Structure Interferometer with Interpretable Multitask Deep Learning","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23441","citing_title":"Cross-Architectural Mixture-of-Experts with Adaptive Soft Routing for Plant Leaf Disease Classification","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":160,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23000","citing_title":"MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations","ref_index":299,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22394","citing_title":"Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21743","citing_title":"Cohort Organized Learning: Clustering Through Agreement","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21139","citing_title":"PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":273,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20027","citing_title":"QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19888","citing_title":"SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17055","citing_title":"T-Rex: Tactile-Reactive Dexterous Manipulation","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2606.15516","citing_title":"Transferring Contact, Not Just Motion: Compliant Grasping Across Dexterous Hands","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13528","citing_title":"What's Old is New Again: Classical Dimensionality Reduction for Efficient Saliency-Guided Biometric Attack Detection","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13168","citing_title":"When Does Routing Become Interpretable? Causal Probes on Block Attention Residuals","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13252","citing_title":"To GAN or Not To GAN: Segmentation Analysis on Mars DEM","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11595","citing_title":"Wavelet-Based Extraction of Transient Noise in Gravitational-Wave Interferometers using a Saliency-Guided Learning Architecture","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12334","citing_title":"Fourier Features Let Agents Learn High Precision Policies with Imitation Learning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09254","citing_title":"Meson-Nucleus Bound States with Neural-Network Quantum States","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":273,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07374","citing_title":"Beyond Backscatter: InSAR coherence from detected SAR images","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01205","citing_title":"Linkify: Learning from Interface-Augmented Assembly Graphs","ref_index":101,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02102","citing_title":"Spectrum Anomaly Detection in OFDMA Systems: Simulation Framework and Benchmark Dataset","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02780","citing_title":"Do Value Vectors in Deep Layers Need Context from the Residual Stream?","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX","json":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX.json","graph_json":"https://pith.science/api/pith-number/PCFYDLTODMVFSOODEHBMBTOTEX/graph.json","events_json":"https://pith.science/api/pith-number/PCFYDLTODMVFSOODEHBMBTOTEX/events.json","paper":"https://pith.science/paper/PCFYDLTO"},"agent_actions":{"view_html":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX","download_json":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX.json","view_paper":"https://pith.science/paper/PCFYDLTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.03385&json=true","fetch_graph":"https://pith.science/api/pith-number/PCFYDLTODMVFSOODEHBMBTOTEX/graph.json","fetch_events":"https://pith.science/api/pith-number/PCFYDLTODMVFSOODEHBMBTOTEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX/action/storage_attestation","attest_author":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX/action/author_attestation","sign_citation":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX/action/citation_signature","submit_replication":"https://pith.science/pith/PCFYDLTODMVFSOODEHBMBTOTEX/action/replication_record"}},"created_at":"2026-07-04T20:43:20.475795+00:00","updated_at":"2026-07-04T20:43:20.475795+00:00"}