{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6XYIBBZIUGU3TQMYDWF3I64A5L","short_pith_number":"pith:6XYIBBZI","schema_version":"1.0","canonical_sha256":"f5f0808728a1a9b9c1981d8bb47b80eae1c7b0e203595f710c9b4bc5e266c9d5","source":{"kind":"arxiv","id":"1810.12885","version":1},"attestation_state":"computed","paper":{"title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Jianfeng Gao, Jingjing Liu, Kevin Duh, Sheng Zhang, XiaoDong Liu","submitted_at":"2018-10-30T17:32:16Z","abstract_excerpt":"We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Experiments on this dataset demonstrate that the performance of state-of-the-art MRC systems fall far behind human performance. ReCoRD represents a challenge for future research to bridge the gap between human and machine commonsense reading comprehension. ReCoRD is available at http://nlp.jhu.edu/record."},"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":"1810.12885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T17:32:16Z","cross_cats_sorted":[],"title_canon_sha256":"ff20c2c554901d440a26ca86a137495c715eae382eab6a9844d5438238d9ba70","abstract_canon_sha256":"348d3be040214fd074bf2fa0792b7ca354aed0f693fa099a9901d6f1ac9b1b88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:53.919736Z","signature_b64":"ddu9U/jJ/JQgyoFWWbELrXi2aOaKLp+2bnSZPBL73IQgO6f0cAplyPca7ji1AirJZ99K0LgSMVjFsgtyuUO0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5f0808728a1a9b9c1981d8bb47b80eae1c7b0e203595f710c9b4bc5e266c9d5","last_reissued_at":"2026-05-18T00:01:53.919353Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:53.919353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Jianfeng Gao, Jingjing Liu, Kevin Duh, Sheng Zhang, XiaoDong Liu","submitted_at":"2018-10-30T17:32:16Z","abstract_excerpt":"We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Experiments on this dataset demonstrate that the performance of state-of-the-art MRC systems fall far behind human performance. ReCoRD represents a challenge for future research to bridge the gap between human and machine commonsense reading comprehension. ReCoRD is available at http://nlp.jhu.edu/record."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12885","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":"1810.12885","created_at":"2026-05-18T00:01:53.919411+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12885v1","created_at":"2026-05-18T00:01:53.919411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12885","created_at":"2026-05-18T00:01:53.919411+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XYIBBZIUGU3","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XYIBBZIUGU3TQMY","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XYIBBZI","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2511.21285","citing_title":"PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2512.02764","citing_title":"PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2405.14782","citing_title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","ref_index":205,"is_internal_anchor":true},{"citing_arxiv_id":"2601.03448","citing_title":"Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2311.16867","citing_title":"The Falcon Series of Open Language Models","ref_index":239,"is_internal_anchor":true},{"citing_arxiv_id":"2111.09543","citing_title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2002.08910","citing_title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"1905.00537","citing_title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","ref_index":153,"is_internal_anchor":true},{"citing_arxiv_id":"2110.08207","citing_title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2303.17564","citing_title":"BloombergGPT: A Large Language Model for Finance","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2306.01116","citing_title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2305.13048","citing_title":"RWKV: Reinventing RNNs for the Transformer Era","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"1905.10044","citing_title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2006.03654","citing_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2202.08906","citing_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","ref_index":215,"is_internal_anchor":false},{"citing_arxiv_id":"2311.12983","citing_title":"GAIA: a benchmark for General AI Assistants","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"1611.09268","citing_title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"1910.10683","citing_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2104.08691","citing_title":"The Power of Scale for Parameter-Efficient Prompt Tuning","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06708","citing_title":"Visual Text Compression as Measure Transport","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18264","citing_title":"Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L","json":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L.json","graph_json":"https://pith.science/api/pith-number/6XYIBBZIUGU3TQMYDWF3I64A5L/graph.json","events_json":"https://pith.science/api/pith-number/6XYIBBZIUGU3TQMYDWF3I64A5L/events.json","paper":"https://pith.science/paper/6XYIBBZI"},"agent_actions":{"view_html":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L","download_json":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L.json","view_paper":"https://pith.science/paper/6XYIBBZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12885&json=true","fetch_graph":"https://pith.science/api/pith-number/6XYIBBZIUGU3TQMYDWF3I64A5L/graph.json","fetch_events":"https://pith.science/api/pith-number/6XYIBBZIUGU3TQMYDWF3I64A5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L/action/storage_attestation","attest_author":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L/action/author_attestation","sign_citation":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L/action/citation_signature","submit_replication":"https://pith.science/pith/6XYIBBZIUGU3TQMYDWF3I64A5L/action/replication_record"}},"created_at":"2026-05-18T00:01:53.919411+00:00","updated_at":"2026-05-18T00:01:53.919411+00:00"}