{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2GMPFPXQTHELIN7EC6KRINMZIL","short_pith_number":"pith:2GMPFPXQ","schema_version":"1.0","canonical_sha256":"d198f2bef099c8b437e4179514359942c9c7d88bdabbdd3d1a4b570f6ba26db2","source":{"kind":"arxiv","id":"1810.09305","version":1},"attestation_state":"computed","paper":{"title":"WikiHow: A Large Scale Text Summarization Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mahnaz Koupaee, William Yang Wang","submitted_at":"2018-10-18T05:29:41Z","abstract_excerpt":"Sequence-to-sequence models have recently gained the state of the art performance in summarization. However, not too many large-scale high-quality datasets are available and almost all the available ones are mainly news articles with specific writing style. Moreover, abstractive human-style systems involving description of the content at a deeper level require data with higher levels of abstraction. In this paper, we present WikiHow, a dataset of more than 230,000 article and summary pairs extracted and constructed from an online knowledge base written by different human authors. The articles "},"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":"1810.09305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-18T05:29:41Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c12097ccd22863053b5bcee8f443823226ce389e737cfe054930be6941c5ad4e","abstract_canon_sha256":"1737b8460e140c8a74b449d0c8982459d74e065347a494ded6aa8453b9600984"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:40.524993Z","signature_b64":"OsfQp2FE8FNdZxypZrh12kG30kj8nKa8gO2q5gGDNh9NLFgNzrYCuBpz1NT/gf3GyNcVdrN5RE8/3O4pz3pADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d198f2bef099c8b437e4179514359942c9c7d88bdabbdd3d1a4b570f6ba26db2","last_reissued_at":"2026-05-18T00:02:40.524545Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:40.524545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WikiHow: A Large Scale Text Summarization Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mahnaz Koupaee, William Yang Wang","submitted_at":"2018-10-18T05:29:41Z","abstract_excerpt":"Sequence-to-sequence models have recently gained the state of the art performance in summarization. However, not too many large-scale high-quality datasets are available and almost all the available ones are mainly news articles with specific writing style. Moreover, abstractive human-style systems involving description of the content at a deeper level require data with higher levels of abstraction. In this paper, we present WikiHow, a dataset of more than 230,000 article and summary pairs extracted and constructed from an online knowledge base written by different human authors. The articles "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09305","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":"1810.09305","created_at":"2026-05-18T00:02:40.524609+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.09305v1","created_at":"2026-05-18T00:02:40.524609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09305","created_at":"2026-05-18T00:02:40.524609+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GMPFPXQTHEL","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GMPFPXQTHELIN7E","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GMPFPXQ","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.23651","citing_title":"How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework","ref_index":133,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23651","citing_title":"How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework","ref_index":105,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08722","citing_title":"What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":214,"is_internal_anchor":true},{"citing_arxiv_id":"2403.09227","citing_title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2410.13848","citing_title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04227","citing_title":"Pro$^2$Assist: Continuous Step-Aware Proactive Assistance with Multimodal Egocentric Perception for Long-Horizon Procedural Tasks","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00597","citing_title":"MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase Extraction","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10302","citing_title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17197","citing_title":"Learning to Control Summaries with Score Ranking","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL","json":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL.json","graph_json":"https://pith.science/api/pith-number/2GMPFPXQTHELIN7EC6KRINMZIL/graph.json","events_json":"https://pith.science/api/pith-number/2GMPFPXQTHELIN7EC6KRINMZIL/events.json","paper":"https://pith.science/paper/2GMPFPXQ"},"agent_actions":{"view_html":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL","download_json":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL.json","view_paper":"https://pith.science/paper/2GMPFPXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.09305&json=true","fetch_graph":"https://pith.science/api/pith-number/2GMPFPXQTHELIN7EC6KRINMZIL/graph.json","fetch_events":"https://pith.science/api/pith-number/2GMPFPXQTHELIN7EC6KRINMZIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL/action/storage_attestation","attest_author":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL/action/author_attestation","sign_citation":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL/action/citation_signature","submit_replication":"https://pith.science/pith/2GMPFPXQTHELIN7EC6KRINMZIL/action/replication_record"}},"created_at":"2026-05-18T00:02:40.524609+00:00","updated_at":"2026-05-18T00:02:40.524609+00:00"}