{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VZAKPAF3BX3WVIBULPFEVDWXFS","short_pith_number":"pith:VZAKPAF3","schema_version":"1.0","canonical_sha256":"ae40a780bb0df76aa0345bca4a8ed72c913e944824d1103526e169c43a7f6248","source":{"kind":"arxiv","id":"2607.21274","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dimitris Garefalakis, Dimitris Plexousakis, Katerina Papantoniou, Nikos Vardakis, Panagiotis Papadakos, Theodore Patkos","submitted_at":"2026-07-23T12:51:55Z","abstract_excerpt":"We present CUP, a Greek book retrieval benchmark consisting of 868 catalog records and 104 expert-annotated queries with graded relevance judgments. We evaluate sparse (BM25), dense (sentence-transformers), hybrid, and LLM-assisted retrieval methods in this book-search setting. Multilingual embeddings outperform Greek-specific models, while hybrid retrieval performs best overall. A query-level analysis shows that BM25 excels at named-entity queries, while dense and hybrid methods improve natural-language, noisy, cross-lingual, and concept queries. Field-aware prompting has model-specific effec"},"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":"2607.21274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T12:51:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"604963ab2143dff04035d98439315d94adcfd16a37968ee019c3ec7d48f189df","abstract_canon_sha256":"8acccb99163aaf52ebb748c0fd10929541f831d6eeca5e45fc242b3f8579cbc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:23.219328Z","signature_b64":"myHylEVHk/GVUbpS1XIMLUFpLvNOTLbcWwv8oq8vL2Wmdtx0xiSn22bcczOAitnnxh1nQQzFujrdpFGxghA8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae40a780bb0df76aa0345bca4a8ed72c913e944824d1103526e169c43a7f6248","last_reissued_at":"2026-07-24T01:24:23.218379Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:23.218379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dimitris Garefalakis, Dimitris Plexousakis, Katerina Papantoniou, Nikos Vardakis, Panagiotis Papadakos, Theodore Patkos","submitted_at":"2026-07-23T12:51:55Z","abstract_excerpt":"We present CUP, a Greek book retrieval benchmark consisting of 868 catalog records and 104 expert-annotated queries with graded relevance judgments. We evaluate sparse (BM25), dense (sentence-transformers), hybrid, and LLM-assisted retrieval methods in this book-search setting. Multilingual embeddings outperform Greek-specific models, while hybrid retrieval performs best overall. A query-level analysis shows that BM25 excels at named-entity queries, while dense and hybrid methods improve natural-language, noisy, cross-lingual, and concept queries. Field-aware prompting has model-specific effec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21274","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/2607.21274/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":"2607.21274","created_at":"2026-07-24T01:24:23.218830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21274v1","created_at":"2026-07-24T01:24:23.218830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21274","created_at":"2026-07-24T01:24:23.218830+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZAKPAF3BX3W","created_at":"2026-07-24T01:24:23.218830+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZAKPAF3BX3WVIBU","created_at":"2026-07-24T01:24:23.218830+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZAKPAF3","created_at":"2026-07-24T01:24:23.218830+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/VZAKPAF3BX3WVIBULPFEVDWXFS","json":"https://pith.science/pith/VZAKPAF3BX3WVIBULPFEVDWXFS.json","graph_json":"https://pith.science/api/pith-number/VZAKPAF3BX3WVIBULPFEVDWXFS/graph.json","events_json":"https://pith.science/api/pith-number/VZAKPAF3BX3WVIBULPFEVDWXFS/events.json","paper":"https://pith.science/paper/VZAKPAF3"},"agent_actions":{"view_html":"https://pith.science/pith/VZAKPAF3BX3WVIBULPFEVDWXFS","download_json":"https://pith.science/pith/VZAKPAF3BX3WVIBULPFEVDWXFS.json","view_paper":"https://pith.science/paper/VZAKPAF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21274&json=true","fetch_graph":"https://pith.science/api/pith-number/VZAKPAF3BX3WVIBULPFEVDWXFS/graph.json","fetch_events":"https://pith.science/api/pith-number/VZAKPAF3BX3WVIBULPFEVDWXFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZAKPAF3BX3WVIBULPFEVDWXFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZAKPAF3BX3WVIBULPFEVDWXFS/action/storage_attestation","attest_author":"https://pith.science/pith/VZAKPAF3BX3WVIBULPFEVDWXFS/action/author_attestation","sign_citation":"https://pith.science/pith/VZAKPAF3BX3WVIBULPFEVDWXFS/action/citation_signature","submit_replication":"https://pith.science/pith/VZAKPAF3BX3WVIBULPFEVDWXFS/action/replication_record"}},"created_at":"2026-07-24T01:24:23.218830+00:00","updated_at":"2026-07-24T01:24:23.218830+00:00"}