{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MBFVXNGNCRLSNWR75KXPPV4VKW","short_pith_number":"pith:MBFVXNGN","schema_version":"1.0","canonical_sha256":"604b5bb4cd145726da3feaaef7d795559cbae8080e78ca1c1756eca1439add82","source":{"kind":"arxiv","id":"2505.18059","version":1},"attestation_state":"computed","paper":{"title":"Assessing the performance of 8 AI chatbots in bibliographic reference retrieval: Grok and DeepSeek outperform ChatGPT, but none are fully accurate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"\\'Alvaro Cabezas-Clavijo, Pavel Sidorenko-Bautista","submitted_at":"2025-05-23T16:07:14Z","abstract_excerpt":"This study analyzes the performance of eight generative artificial intelligence chatbots -- ChatGPT, Claude, Copilot, DeepSeek, Gemini, Grok, Le Chat, and Perplexity -- in their free versions, in the task of generating academic bibliographic references within the university context. A total of 400 references were evaluated across the five major areas of knowledge (Health, Engineering, Experimental Sciences, Social Sciences, and Humanities), based on a standardized prompt. Each reference was assessed according to five key components (authorship, year, title, source, and location), along with do"},"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":"2505.18059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-23T16:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"d9427e03af36182634064c100f518f9a57f48c9947ffed65c60f4ea4cfb0ee06","abstract_canon_sha256":"a6f14e2bc5e1df40ee8e3ee647e3ae89b48ebc19703186c4cdbaefbda9852289"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:09.649303Z","signature_b64":"9PdmirpcVG8GqhwlEtxzsbIaZ2kA8ub68XJXWM4epRrLQhRT2YAkv2ueA5BfUVsWMcetXkWrvx/6OmIhdE0YBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"604b5bb4cd145726da3feaaef7d795559cbae8080e78ca1c1756eca1439add82","last_reissued_at":"2026-05-20T00:04:09.648465Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:09.648465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the performance of 8 AI chatbots in bibliographic reference retrieval: Grok and DeepSeek outperform ChatGPT, but none are fully accurate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"\\'Alvaro Cabezas-Clavijo, Pavel Sidorenko-Bautista","submitted_at":"2025-05-23T16:07:14Z","abstract_excerpt":"This study analyzes the performance of eight generative artificial intelligence chatbots -- ChatGPT, Claude, Copilot, DeepSeek, Gemini, Grok, Le Chat, and Perplexity -- in their free versions, in the task of generating academic bibliographic references within the university context. A total of 400 references were evaluated across the five major areas of knowledge (Health, Engineering, Experimental Sciences, Social Sciences, and Humanities), based on a standardized prompt. Each reference was assessed according to five key components (authorship, year, title, source, and location), along with do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18059","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/2505.18059/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":"2505.18059","created_at":"2026-05-20T00:04:09.648600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18059v1","created_at":"2026-05-20T00:04:09.648600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18059","created_at":"2026-05-20T00:04:09.648600+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBFVXNGNCRLS","created_at":"2026-05-20T00:04:09.648600+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBFVXNGNCRLSNWR7","created_at":"2026-05-20T00:04:09.648600+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBFVXNGN","created_at":"2026-05-20T00:04:09.648600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW","json":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW.json","graph_json":"https://pith.science/api/pith-number/MBFVXNGNCRLSNWR75KXPPV4VKW/graph.json","events_json":"https://pith.science/api/pith-number/MBFVXNGNCRLSNWR75KXPPV4VKW/events.json","paper":"https://pith.science/paper/MBFVXNGN"},"agent_actions":{"view_html":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW","download_json":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW.json","view_paper":"https://pith.science/paper/MBFVXNGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18059&json=true","fetch_graph":"https://pith.science/api/pith-number/MBFVXNGNCRLSNWR75KXPPV4VKW/graph.json","fetch_events":"https://pith.science/api/pith-number/MBFVXNGNCRLSNWR75KXPPV4VKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW/action/storage_attestation","attest_author":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW/action/author_attestation","sign_citation":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW/action/citation_signature","submit_replication":"https://pith.science/pith/MBFVXNGNCRLSNWR75KXPPV4VKW/action/replication_record"}},"created_at":"2026-05-20T00:04:09.648600+00:00","updated_at":"2026-05-20T00:04:09.648600+00:00"}