{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SS53DYPJDLCMAV76TOW5IVEDQX","short_pith_number":"pith:SS53DYPJ","schema_version":"1.0","canonical_sha256":"94bbb1e1e91ac4c057fe9badd4548385cc284142f051e41f355c070fb773e48e","source":{"kind":"arxiv","id":"1704.05426","version":4},"attestation_state":"computed","paper":{"title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adina Williams, Nikita Nangia, Samuel R. Bowman","submitted_at":"2017-04-18T17:10:13Z","abstract_excerpt":"This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding. In addition to being one of the largest corpora available for the task of NLI, at 433k examples, this corpus improves upon available resources in its coverage: it offers data from ten distinct genres of written and spoken English--making it possible to evaluate systems on nearly the full complexity of the language--and it offers an explicit setting for the evaluation of cross-genre domain adaptati"},"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":"1704.05426","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-18T17:10:13Z","cross_cats_sorted":[],"title_canon_sha256":"d6cc4868f4281958387e525a62ecd969bcaed6dfe1e1b9870781b8ab8bd44f80","abstract_canon_sha256":"e8bc98199d6e253c0c519a974be9f76dab030ae66260c9f048f6246fca84b5fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:59.476892Z","signature_b64":"SoaUGFqe9IdM36PdHwipNhcr6ihMLCuhx87g0MkO5LLNSN9BiM7pP0wmOakTf9321svxUTy+n2STme5ak+UaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94bbb1e1e91ac4c057fe9badd4548385cc284142f051e41f355c070fb773e48e","last_reissued_at":"2026-05-18T00:22:59.476283Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:59.476283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adina Williams, Nikita Nangia, Samuel R. Bowman","submitted_at":"2017-04-18T17:10:13Z","abstract_excerpt":"This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding. In addition to being one of the largest corpora available for the task of NLI, at 433k examples, this corpus improves upon available resources in its coverage: it offers data from ten distinct genres of written and spoken English--making it possible to evaluate systems on nearly the full complexity of the language--and it offers an explicit setting for the evaluation of cross-genre domain adaptati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.05426","kind":"arxiv","version":4},"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":"1704.05426","created_at":"2026-05-18T00:22:59.476359+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.05426v4","created_at":"2026-05-18T00:22:59.476359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05426","created_at":"2026-05-18T00:22:59.476359+00:00"},{"alias_kind":"pith_short_12","alias_value":"SS53DYPJDLCM","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SS53DYPJDLCMAV76","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SS53DYPJ","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":43,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"1906.08340","citing_title":"Learning Compressed Sentence Representations for On-Device Text Processing","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09635","citing_title":"Investigating Biases in Textual Entailment Datasets","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2412.19098","citing_title":"SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05338","citing_title":"To Tune or Not To Tune? How About the Best of Both Worlds?","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2402.02249","citing_title":"Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2408.01119","citing_title":"Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21726","citing_title":"Probabilistic Attribution For Large Language Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20771","citing_title":"Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16608","citing_title":"To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16704","citing_title":"Convex Dataset Valuation for Post-Training","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17152","citing_title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages","ref_index":216,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14260","citing_title":"On the Burden of Achieving Fairness in Conformal Prediction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22226","citing_title":"Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00994","citing_title":"Should We Still Pretrain Encoders with Masked Language Modeling?","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15707","citing_title":"Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09696","citing_title":"Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2301.12652","citing_title":"REPLUG: Retrieval-Augmented Black-Box Language Models","ref_index":209,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21285","citing_title":"PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2512.02764","citing_title":"PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07538","citing_title":"SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02543","citing_title":"Norm Anchors Make Model Edits Last","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14233","citing_title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2303.08896","citing_title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2104.08821","citing_title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14260","citing_title":"On the Burden of Achieving Fairness in Conformal Prediction","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX","json":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX.json","graph_json":"https://pith.science/api/pith-number/SS53DYPJDLCMAV76TOW5IVEDQX/graph.json","events_json":"https://pith.science/api/pith-number/SS53DYPJDLCMAV76TOW5IVEDQX/events.json","paper":"https://pith.science/paper/SS53DYPJ"},"agent_actions":{"view_html":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX","download_json":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX.json","view_paper":"https://pith.science/paper/SS53DYPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.05426&json=true","fetch_graph":"https://pith.science/api/pith-number/SS53DYPJDLCMAV76TOW5IVEDQX/graph.json","fetch_events":"https://pith.science/api/pith-number/SS53DYPJDLCMAV76TOW5IVEDQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX/action/storage_attestation","attest_author":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX/action/author_attestation","sign_citation":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX/action/citation_signature","submit_replication":"https://pith.science/pith/SS53DYPJDLCMAV76TOW5IVEDQX/action/replication_record"}},"created_at":"2026-05-18T00:22:59.476359+00:00","updated_at":"2026-05-18T00:22:59.476359+00:00"}