{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2367R2ZIV2Z2NBEX3N6SXQKDTY","short_pith_number":"pith:2367R2ZI","schema_version":"1.0","canonical_sha256":"d6fdf8eb28aeb3a68497db7d2bc1439e30588c9082843273f3d7e0b6a77888ec","source":{"kind":"arxiv","id":"2110.10774","version":1},"attestation_state":"computed","paper":{"title":"SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hideki Nakayama, Hiroya Takamura, Hong Chen","submitted_at":"2021-10-20T20:37:11Z","abstract_excerpt":"Generating texts in scientific papers requires not only capturing the content contained within the given input but also frequently acquiring the external information called \\textit{context}. We push forward the scientific text generation by proposing a new task, namely \\textbf{context-aware text generation} in the scientific domain, aiming at exploiting the contributions of context in generated texts. To this end, we present a novel challenging large-scale \\textbf{Sci}entific Paper Dataset for Conte\\textbf{X}t-Aware Text \\textbf{Gen}eration (SciXGen), consisting of well-annotated 205,304 paper"},"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":"2110.10774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T20:37:11Z","cross_cats_sorted":[],"title_canon_sha256":"057886f9ace77690247ecb4e85199a615f3eee8ab7a9d7d9dac98b5cad8f48ef","abstract_canon_sha256":"cad7741399a773ffdf5e6019f36f9aea8881807ed9362a58a15e0feaf1471018"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:32.195983Z","signature_b64":"fkNYw2Qb7V19QyTR57H5uIDBf8hZnY9F1VZcW8BTAuhZCOe3WhqZgBRk9v2vMckEPJzkVP771AQUWLCrSTwEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6fdf8eb28aeb3a68497db7d2bc1439e30588c9082843273f3d7e0b6a77888ec","last_reissued_at":"2026-07-05T03:24:32.195424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:32.195424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hideki Nakayama, Hiroya Takamura, Hong Chen","submitted_at":"2021-10-20T20:37:11Z","abstract_excerpt":"Generating texts in scientific papers requires not only capturing the content contained within the given input but also frequently acquiring the external information called \\textit{context}. We push forward the scientific text generation by proposing a new task, namely \\textbf{context-aware text generation} in the scientific domain, aiming at exploiting the contributions of context in generated texts. To this end, we present a novel challenging large-scale \\textbf{Sci}entific Paper Dataset for Conte\\textbf{X}t-Aware Text \\textbf{Gen}eration (SciXGen), consisting of well-annotated 205,304 paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10774","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.10774/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.10774","created_at":"2026-07-05T03:24:32.195502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10774v1","created_at":"2026-07-05T03:24:32.195502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10774","created_at":"2026-07-05T03:24:32.195502+00:00"},{"alias_kind":"pith_short_12","alias_value":"2367R2ZIV2Z2","created_at":"2026-07-05T03:24:32.195502+00:00"},{"alias_kind":"pith_short_16","alias_value":"2367R2ZIV2Z2NBEX","created_at":"2026-07-05T03:24:32.195502+00:00"},{"alias_kind":"pith_short_8","alias_value":"2367R2ZI","created_at":"2026-07-05T03:24:32.195502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25281","citing_title":"READER: Reasoning-Enhanced AI-Generated Text Detection","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY","json":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY.json","graph_json":"https://pith.science/api/pith-number/2367R2ZIV2Z2NBEX3N6SXQKDTY/graph.json","events_json":"https://pith.science/api/pith-number/2367R2ZIV2Z2NBEX3N6SXQKDTY/events.json","paper":"https://pith.science/paper/2367R2ZI"},"agent_actions":{"view_html":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY","download_json":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY.json","view_paper":"https://pith.science/paper/2367R2ZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10774&json=true","fetch_graph":"https://pith.science/api/pith-number/2367R2ZIV2Z2NBEX3N6SXQKDTY/graph.json","fetch_events":"https://pith.science/api/pith-number/2367R2ZIV2Z2NBEX3N6SXQKDTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY/action/storage_attestation","attest_author":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY/action/author_attestation","sign_citation":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY/action/citation_signature","submit_replication":"https://pith.science/pith/2367R2ZIV2Z2NBEX3N6SXQKDTY/action/replication_record"}},"created_at":"2026-07-05T03:24:32.195502+00:00","updated_at":"2026-07-05T03:24:32.195502+00:00"}