{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PHH2I2BMDMDSQ6WC3KXRISEC4V","short_pith_number":"pith:PHH2I2BM","schema_version":"1.0","canonical_sha256":"79cfa4682c1b07287ac2daaf144882e54dacf21f9e3fcfffc0763a3f18801ebe","source":{"kind":"arxiv","id":"1511.02301","version":4},"attestation_state":"computed","paper":{"title":"The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antoine Bordes, Felix Hill, Jason Weston, Sumit Chopra","submitted_at":"2015-11-07T04:36:20Z","abstract_excerpt":"We introduce a new test of how well language models capture meaning in children's books. Unlike standard language modelling benchmarks, it distinguishes the task of predicting syntactic function words from that of predicting lower-frequency words, which carry greater semantic content. We compare a range of state-of-the-art models, each with a different way of encoding what has been previously read. We show that models which store explicit representations of long-term contexts outperform state-of-the-art neural language models at predicting semantic content words, although this advantage is not"},"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":"1511.02301","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-07T04:36:20Z","cross_cats_sorted":[],"title_canon_sha256":"c7919aca1b1963e506a5278fd252410db0daa94d58b0bdc331462f339f9daaf7","abstract_canon_sha256":"52746aa2db9095d76a4c874a54e107443c29aeedfd3f108b2afd8c9af2befa9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:55.325470Z","signature_b64":"gdVOkLilpj8pq3+KV7wczs4cCTSdu47zdmtYxT1sd3PdAH/6VTFikUfS9PaIYiv8+lyr6d6L1RUwIcBlcnxyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79cfa4682c1b07287ac2daaf144882e54dacf21f9e3fcfffc0763a3f18801ebe","last_reissued_at":"2026-05-18T01:17:55.324835Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:55.324835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antoine Bordes, Felix Hill, Jason Weston, Sumit Chopra","submitted_at":"2015-11-07T04:36:20Z","abstract_excerpt":"We introduce a new test of how well language models capture meaning in children's books. Unlike standard language modelling benchmarks, it distinguishes the task of predicting syntactic function words from that of predicting lower-frequency words, which carry greater semantic content. We compare a range of state-of-the-art models, each with a different way of encoding what has been previously read. We show that models which store explicit representations of long-term contexts outperform state-of-the-art neural language models at predicting semantic content words, although this advantage is not"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.02301","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":"1511.02301","created_at":"2026-05-18T01:17:55.324927+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.02301v4","created_at":"2026-05-18T01:17:55.324927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.02301","created_at":"2026-05-18T01:17:55.324927+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHH2I2BMDMDS","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHH2I2BMDMDSQ6WC","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHH2I2BM","created_at":"2026-05-18T12:29:37.295048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1907.00708","citing_title":"EQuANt (Enhanced Question Answer Network)","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01686","citing_title":"Machine Reading Comprehension: a Literature Review","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1911.05507","citing_title":"Compressive Transformers for Long-Range Sequence Modelling","ref_index":125,"is_internal_anchor":true},{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":220,"is_internal_anchor":true},{"citing_arxiv_id":"2001.04451","citing_title":"Reformer: The Efficient Transformer","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"1705.03551","citing_title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10390","citing_title":"LLM-PRISM: Characterizing Silent Data Corruption from Permanent GPU Faults in LLM Training","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V","json":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V.json","graph_json":"https://pith.science/api/pith-number/PHH2I2BMDMDSQ6WC3KXRISEC4V/graph.json","events_json":"https://pith.science/api/pith-number/PHH2I2BMDMDSQ6WC3KXRISEC4V/events.json","paper":"https://pith.science/paper/PHH2I2BM"},"agent_actions":{"view_html":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V","download_json":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V.json","view_paper":"https://pith.science/paper/PHH2I2BM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.02301&json=true","fetch_graph":"https://pith.science/api/pith-number/PHH2I2BMDMDSQ6WC3KXRISEC4V/graph.json","fetch_events":"https://pith.science/api/pith-number/PHH2I2BMDMDSQ6WC3KXRISEC4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V/action/storage_attestation","attest_author":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V/action/author_attestation","sign_citation":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V/action/citation_signature","submit_replication":"https://pith.science/pith/PHH2I2BMDMDSQ6WC3KXRISEC4V/action/replication_record"}},"created_at":"2026-05-18T01:17:55.324927+00:00","updated_at":"2026-05-18T01:17:55.324927+00:00"}