{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:262KHMRZGJF6KAQSOPSFOIHNK3","short_pith_number":"pith:262KHMRZ","schema_version":"1.0","canonical_sha256":"d7b4a3b239324be5021273e45720ed56e44f22ca99ecbfa8cf698767eca426f1","source":{"kind":"arxiv","id":"1812.01718","version":1},"attestation_state":"computed","paper":{"title":"Deep Learning for Classical Japanese Literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alex Lamb, Asanobu Kitamoto, David Ha, Kazuaki Yamamoto, Mikel Bober-Irizar, Tarin Clanuwat","submitted_at":"2018-12-03T12:37:31Z","abstract_excerpt":"Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance. In this work, we introduce Kuzushiji-MNIST, a dataset which focuses on Kuzushiji (cursive Japanese), as well as two larger, more challenging datasets, Kuzushiji-49 and Kuzushiji-Kan"},"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":"1812.01718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-12-03T12:37:31Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"851e9350c8aed4982f654e254314019ee78a80a352155cc651e55c03e4895044","abstract_canon_sha256":"909dacc168ed9e8a24627c442e61b0808dc2a2159cbb48e94119aed416b10f29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:00.798688Z","signature_b64":"hC6V4/RYeeZ2w7JNF3jniCdpeaAkza+QV96gy3yr4gfTuTSlvQue3+HCSsRzV9ZSItS3edng4HT+gChrz8i3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7b4a3b239324be5021273e45720ed56e44f22ca99ecbfa8cf698767eca426f1","last_reissued_at":"2026-05-17T23:59:00.798097Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:00.798097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning for Classical Japanese Literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alex Lamb, Asanobu Kitamoto, David Ha, Kazuaki Yamamoto, Mikel Bober-Irizar, Tarin Clanuwat","submitted_at":"2018-12-03T12:37:31Z","abstract_excerpt":"Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance. In this work, we introduce Kuzushiji-MNIST, a dataset which focuses on Kuzushiji (cursive Japanese), as well as two larger, more challenging datasets, Kuzushiji-49 and Kuzushiji-Kan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01718","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":""},"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":"1812.01718","created_at":"2026-05-17T23:59:00.798182+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01718v1","created_at":"2026-05-17T23:59:00.798182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01718","created_at":"2026-05-17T23:59:00.798182+00:00"},{"alias_kind":"pith_short_12","alias_value":"262KHMRZGJF6","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"262KHMRZGJF6KAQS","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"262KHMRZ","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"1907.11519","citing_title":"Context-Aware Multipath Networks","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2504.07031","citing_title":"Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22155","citing_title":"Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2506.15412","citing_title":"Partitioning for Intrinsic Model Inversion Resistance in Collaborative Inference","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19409","citing_title":"Unlocking the Potential of Continual Model Merging: An ODE Perspective","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21324","citing_title":"Stimulus symmetries can confound representational similarity analyses","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19409","citing_title":"Unlocking the Potential of Continual Model Merging: An ODE Perspective","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16882","citing_title":"E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2512.00676","citing_title":"Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2603.02945","citing_title":"ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12843","citing_title":"Bayesian Model Merging","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10954","citing_title":"Controlled Steering-Based State Preparation for Adversarial-Robust Quantum Machine Learning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08135","citing_title":"Dendritic Neural Networks with Equilibrium Propagation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01580","citing_title":"Model Merging: Foundations and Algorithms","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00600","citing_title":"Possibilistic Predictive Uncertainty for Deep Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00747","citing_title":"Quantum Interval Bound Propagation for Certified Training of Quantum Neural Networks","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00107","citing_title":"Efficient Mutation Testing of Quantum Machine Learning Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12935","citing_title":"Task Alignment: A simple and effective proxy for model merging in computer vision","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04059","citing_title":"Continual Distillation of Teachers from Different Domains","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07413","citing_title":"Risk-Consistent Multiclass Learning from Random Label-Subset Membership Queries","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17673","citing_title":"Grokking of Diffusion Models: Case Study on Modular Addition","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3","json":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3.json","graph_json":"https://pith.science/api/pith-number/262KHMRZGJF6KAQSOPSFOIHNK3/graph.json","events_json":"https://pith.science/api/pith-number/262KHMRZGJF6KAQSOPSFOIHNK3/events.json","paper":"https://pith.science/paper/262KHMRZ"},"agent_actions":{"view_html":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3","download_json":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3.json","view_paper":"https://pith.science/paper/262KHMRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01718&json=true","fetch_graph":"https://pith.science/api/pith-number/262KHMRZGJF6KAQSOPSFOIHNK3/graph.json","fetch_events":"https://pith.science/api/pith-number/262KHMRZGJF6KAQSOPSFOIHNK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3/action/storage_attestation","attest_author":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3/action/author_attestation","sign_citation":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3/action/citation_signature","submit_replication":"https://pith.science/pith/262KHMRZGJF6KAQSOPSFOIHNK3/action/replication_record"}},"created_at":"2026-05-17T23:59:00.798182+00:00","updated_at":"2026-05-17T23:59:00.798182+00:00"}