{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IWIKLG4AKMU3QAPBPFBGJRF7WI","short_pith_number":"pith:IWIKLG4A","schema_version":"1.0","canonical_sha256":"4590a59b805329b801e1794264c4bfb202e64dafee0a45bca6a78a8a686ade7f","source":{"kind":"arxiv","id":"2401.02187","version":1},"attestation_state":"computed","paper":{"title":"Location Aware Modular Biencoder for Tourism Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haonan Li, Martin Tomko, Timothy Baldwin","submitted_at":"2024-01-04T10:39:58Z","abstract_excerpt":"Answering real-world tourism questions that seek Point-of-Interest (POI) recommendations is challenging, as it requires both spatial and non-spatial reasoning, over a large candidate pool. The traditional method of encoding each pair of question and POI becomes inefficient when the number of candidates increases, making it infeasible for real-world applications. To overcome this, we propose treating the QA task as a dense vector retrieval problem, where we encode questions and POIs separately and retrieve the most relevant POIs for a question by utilizing embedding space similarity. We use pre"},"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":"2401.02187","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T10:39:58Z","cross_cats_sorted":[],"title_canon_sha256":"bf0063d3bae3d66efbc8a96bb2e32b4daec1cb375111a13a11078e0cb6a4cd61","abstract_canon_sha256":"2e14774d9237df7081ad0067e8da6e93be8cd992a4f3a5a4abb3d0974c4d448d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:12.884000Z","signature_b64":"OOlM8SjUm2y3lOuMRw45eBajJ2wKdBDVEGYEImL5D9j5/b9po6Lqf+HzrjaPECyWcYKRTkJjKRXrXjTJ00lqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4590a59b805329b801e1794264c4bfb202e64dafee0a45bca6a78a8a686ade7f","last_reissued_at":"2026-07-05T07:30:12.883543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:12.883543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Location Aware Modular Biencoder for Tourism Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haonan Li, Martin Tomko, Timothy Baldwin","submitted_at":"2024-01-04T10:39:58Z","abstract_excerpt":"Answering real-world tourism questions that seek Point-of-Interest (POI) recommendations is challenging, as it requires both spatial and non-spatial reasoning, over a large candidate pool. The traditional method of encoding each pair of question and POI becomes inefficient when the number of candidates increases, making it infeasible for real-world applications. To overcome this, we propose treating the QA task as a dense vector retrieval problem, where we encode questions and POIs separately and retrieve the most relevant POIs for a question by utilizing embedding space similarity. We use pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02187","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/2401.02187/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":"2401.02187","created_at":"2026-07-05T07:30:12.883598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02187v1","created_at":"2026-07-05T07:30:12.883598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02187","created_at":"2026-07-05T07:30:12.883598+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWIKLG4AKMU3","created_at":"2026-07-05T07:30:12.883598+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWIKLG4AKMU3QAPB","created_at":"2026-07-05T07:30:12.883598+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWIKLG4A","created_at":"2026-07-05T07:30:12.883598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07411","citing_title":"GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI","json":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI.json","graph_json":"https://pith.science/api/pith-number/IWIKLG4AKMU3QAPBPFBGJRF7WI/graph.json","events_json":"https://pith.science/api/pith-number/IWIKLG4AKMU3QAPBPFBGJRF7WI/events.json","paper":"https://pith.science/paper/IWIKLG4A"},"agent_actions":{"view_html":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI","download_json":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI.json","view_paper":"https://pith.science/paper/IWIKLG4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02187&json=true","fetch_graph":"https://pith.science/api/pith-number/IWIKLG4AKMU3QAPBPFBGJRF7WI/graph.json","fetch_events":"https://pith.science/api/pith-number/IWIKLG4AKMU3QAPBPFBGJRF7WI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI/action/storage_attestation","attest_author":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI/action/author_attestation","sign_citation":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI/action/citation_signature","submit_replication":"https://pith.science/pith/IWIKLG4AKMU3QAPBPFBGJRF7WI/action/replication_record"}},"created_at":"2026-07-05T07:30:12.883598+00:00","updated_at":"2026-07-05T07:30:12.883598+00:00"}