{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:TTBLUHGYWRKLNILA76DUVK4LHI","short_pith_number":"pith:TTBLUHGY","schema_version":"1.0","canonical_sha256":"9cc2ba1cd8b454b6a160ff874aab8b3a133d7c8b429c4eb9f517108ea7816df1","source":{"kind":"arxiv","id":"1604.01696","version":1},"attestation_state":"computed","paper":{"title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Devi Parikh, Dhruv Batra, James Allen, Lucy Vanderwende, Nasrin Mostafazadeh, Nathanael Chambers, Pushmeet Kohli, Xiaodong He","submitted_at":"2016-04-06T17:15:10Z","abstract_excerpt":"Representation and learning of commonsense knowledge is one of the foundational problems in the quest to enable deep language understanding. This issue is particularly challenging for understanding casual and correlational relationships between events. While this topic has received a lot of interest in the NLP community, research has been hindered by the lack of a proper evaluation framework. This paper attempts to address this problem with a new framework for evaluating story understanding and script learning: the 'Story Cloze Test'. This test requires a system to choose the correct ending to"},"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":"1604.01696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-06T17:15:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e31bd9784545d284889dc6920217225b687533f54ecdfb800338bf90fe2e970","abstract_canon_sha256":"1198ec1614e4c99b41555149ef631cf166dfd6a9e3a044f98500ba5714af288f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:35.796743Z","signature_b64":"P8UqHp+IIiHa960Te+n5avuC9SyfJhb6W2GEo5R3gbLp48O0i+eDWcwtVCe+nHT0Ht+ekfjPXkWbztwXjl1LAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc2ba1cd8b454b6a160ff874aab8b3a133d7c8b429c4eb9f517108ea7816df1","last_reissued_at":"2026-05-18T01:17:35.795854Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:35.795854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Devi Parikh, Dhruv Batra, James Allen, Lucy Vanderwende, Nasrin Mostafazadeh, Nathanael Chambers, Pushmeet Kohli, Xiaodong He","submitted_at":"2016-04-06T17:15:10Z","abstract_excerpt":"Representation and learning of commonsense knowledge is one of the foundational problems in the quest to enable deep language understanding. This issue is particularly challenging for understanding casual and correlational relationships between events. While this topic has received a lot of interest in the NLP community, research has been hindered by the lack of a proper evaluation framework. This paper attempts to address this problem with a new framework for evaluating story understanding and script learning: the 'Story Cloze Test'. This test requires a system to choose the correct ending to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.01696","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":"1604.01696","created_at":"2026-05-18T01:17:35.795996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.01696v1","created_at":"2026-05-18T01:17:35.795996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.01696","created_at":"2026-05-18T01:17:35.795996+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTBLUHGYWRKL","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTBLUHGYWRKLNILA","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTBLUHGY","created_at":"2026-05-18T12:30:46.583412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2310.11453","citing_title":"BitNet: Scaling 1-bit Transformers for Large Language Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2512.12283","citing_title":"Large Language Models have Chain-of-Affect","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2412.02612","citing_title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2309.14509","citing_title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00195","citing_title":"Diversity in Large Language Models under Supervised Fine-Tuning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00195","citing_title":"Diversity in Large Language Models under Supervised Fine-Tuning","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI","json":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI.json","graph_json":"https://pith.science/api/pith-number/TTBLUHGYWRKLNILA76DUVK4LHI/graph.json","events_json":"https://pith.science/api/pith-number/TTBLUHGYWRKLNILA76DUVK4LHI/events.json","paper":"https://pith.science/paper/TTBLUHGY"},"agent_actions":{"view_html":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI","download_json":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI.json","view_paper":"https://pith.science/paper/TTBLUHGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.01696&json=true","fetch_graph":"https://pith.science/api/pith-number/TTBLUHGYWRKLNILA76DUVK4LHI/graph.json","fetch_events":"https://pith.science/api/pith-number/TTBLUHGYWRKLNILA76DUVK4LHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI/action/storage_attestation","attest_author":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI/action/author_attestation","sign_citation":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI/action/citation_signature","submit_replication":"https://pith.science/pith/TTBLUHGYWRKLNILA76DUVK4LHI/action/replication_record"}},"created_at":"2026-05-18T01:17:35.795996+00:00","updated_at":"2026-05-18T01:17:35.795996+00:00"}