{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4Z7SJ4M32USZXIP5JVAXUEKX7A","short_pith_number":"pith:4Z7SJ4M3","schema_version":"1.0","canonical_sha256":"e67f24f19bd5259ba1fd4d417a1157f81ef2e074b327a7652d6146ee2e113502","source":{"kind":"arxiv","id":"2402.12255","version":1},"attestation_state":"computed","paper":{"title":"Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aahan Tyagi, Anna Martin-Boyle, Dongyeop Kang, Marti A. Hearst","submitted_at":"2024-02-19T16:14:04Z","abstract_excerpt":"Numerous AI-assisted scholarly applications have been developed to aid different stages of the research process. We present an analysis of AI-assisted scholarly writing generated with ScholaCite, a tool we built that is designed for organizing literature and composing Related Work sections for academic papers. Our evaluation method focuses on the analysis of citation graphs to assess the structural complexity and inter-connectedness of citations in texts and involves a three-way comparison between (1) original human-written texts, (2) purely GPT-generated texts, and (3) human-AI collaborative "},"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":"2402.12255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T16:14:04Z","cross_cats_sorted":[],"title_canon_sha256":"f4a8b0c1493175479a5a441354ebdc154449890200d7f7450f290491a9ada043","abstract_canon_sha256":"82523a1b955e9c1f4b24604cdfd93a2ba7bc7f58a5da180e87f260fc80ab5cb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:51.108944Z","signature_b64":"js3VjDQXUYmezVyi65myt3ydm8tkfvyoELKHJANUe7Xd2dJG9fuBBkkiTGXeP38//lvoxNgXN5M2emWEcn9NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e67f24f19bd5259ba1fd4d417a1157f81ef2e074b327a7652d6146ee2e113502","last_reissued_at":"2026-07-05T07:46:51.108554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:51.108554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aahan Tyagi, Anna Martin-Boyle, Dongyeop Kang, Marti A. Hearst","submitted_at":"2024-02-19T16:14:04Z","abstract_excerpt":"Numerous AI-assisted scholarly applications have been developed to aid different stages of the research process. We present an analysis of AI-assisted scholarly writing generated with ScholaCite, a tool we built that is designed for organizing literature and composing Related Work sections for academic papers. Our evaluation method focuses on the analysis of citation graphs to assess the structural complexity and inter-connectedness of citations in texts and involves a three-way comparison between (1) original human-written texts, (2) purely GPT-generated texts, and (3) human-AI collaborative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12255","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/2402.12255/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":"2402.12255","created_at":"2026-07-05T07:46:51.108615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12255v1","created_at":"2026-07-05T07:46:51.108615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12255","created_at":"2026-07-05T07:46:51.108615+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Z7SJ4M32USZ","created_at":"2026-07-05T07:46:51.108615+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Z7SJ4M32USZXIP5","created_at":"2026-07-05T07:46:51.108615+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Z7SJ4M3","created_at":"2026-07-05T07:46:51.108615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19647","citing_title":"Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work Generation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A","json":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A.json","graph_json":"https://pith.science/api/pith-number/4Z7SJ4M32USZXIP5JVAXUEKX7A/graph.json","events_json":"https://pith.science/api/pith-number/4Z7SJ4M32USZXIP5JVAXUEKX7A/events.json","paper":"https://pith.science/paper/4Z7SJ4M3"},"agent_actions":{"view_html":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A","download_json":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A.json","view_paper":"https://pith.science/paper/4Z7SJ4M3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12255&json=true","fetch_graph":"https://pith.science/api/pith-number/4Z7SJ4M32USZXIP5JVAXUEKX7A/graph.json","fetch_events":"https://pith.science/api/pith-number/4Z7SJ4M32USZXIP5JVAXUEKX7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A/action/storage_attestation","attest_author":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A/action/author_attestation","sign_citation":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A/action/citation_signature","submit_replication":"https://pith.science/pith/4Z7SJ4M32USZXIP5JVAXUEKX7A/action/replication_record"}},"created_at":"2026-07-05T07:46:51.108615+00:00","updated_at":"2026-07-05T07:46:51.108615+00:00"}