{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IWXVDN5LE3OV3H5X3GP66SU53G","short_pith_number":"pith:IWXVDN5L","schema_version":"1.0","canonical_sha256":"45af51b7ab26dd5d9fb7d99fef4a9dd9b6cd226b30cb330ad75191df850da3e3","source":{"kind":"arxiv","id":"2407.01409","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Few-Shot Learning for Knowledge Graph Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Zugarini, Jacopo D'Abramo, Paolo Torroni","submitted_at":"2024-07-01T15:59:17Z","abstract_excerpt":"Large language models present opportunities for innovative Question Answering over Knowledge Graphs (KGQA). However, they are not inherently designed for query generation. To bridge this gap, solutions have been proposed that rely on fine-tuning or ad-hoc architectures, achieving good results but limited out-of-domain distribution generalization. In this study, we introduce a novel approach called Dynamic Few-Shot Learning (DFSL). DFSL integrates the efficiency of in-context learning and semantic similarity and provides a generally applicable solution for KGQA with state-of-the-art performance"},"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":"2407.01409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T15:59:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd6f5f8f3ef633b76a66054efb3e0de416abe8d95ba2743f9178462953558fea","abstract_canon_sha256":"70497f764f6415fd00de285e66e1ee23541f804f0599c96f04e368410d481b18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:47.594626Z","signature_b64":"0w8+XK7D6UlFCgeOYpoZ3z5igWITs4SYxQLr2nnuPX5DdUdHfm7uTbyAW14L2nhfL21D1rVXo1UEZWieNLuQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45af51b7ab26dd5d9fb7d99fef4a9dd9b6cd226b30cb330ad75191df850da3e3","last_reissued_at":"2026-07-05T08:38:47.594178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:47.594178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Few-Shot Learning for Knowledge Graph Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Zugarini, Jacopo D'Abramo, Paolo Torroni","submitted_at":"2024-07-01T15:59:17Z","abstract_excerpt":"Large language models present opportunities for innovative Question Answering over Knowledge Graphs (KGQA). However, they are not inherently designed for query generation. To bridge this gap, solutions have been proposed that rely on fine-tuning or ad-hoc architectures, achieving good results but limited out-of-domain distribution generalization. In this study, we introduce a novel approach called Dynamic Few-Shot Learning (DFSL). DFSL integrates the efficiency of in-context learning and semantic similarity and provides a generally applicable solution for KGQA with state-of-the-art performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01409","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/2407.01409/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":"2407.01409","created_at":"2026-07-05T08:38:47.594235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01409v1","created_at":"2026-07-05T08:38:47.594235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01409","created_at":"2026-07-05T08:38:47.594235+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWXVDN5LE3OV","created_at":"2026-07-05T08:38:47.594235+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWXVDN5LE3OV3H5X","created_at":"2026-07-05T08:38:47.594235+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWXVDN5L","created_at":"2026-07-05T08:38:47.594235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.26383","citing_title":"Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G","json":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G.json","graph_json":"https://pith.science/api/pith-number/IWXVDN5LE3OV3H5X3GP66SU53G/graph.json","events_json":"https://pith.science/api/pith-number/IWXVDN5LE3OV3H5X3GP66SU53G/events.json","paper":"https://pith.science/paper/IWXVDN5L"},"agent_actions":{"view_html":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G","download_json":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G.json","view_paper":"https://pith.science/paper/IWXVDN5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01409&json=true","fetch_graph":"https://pith.science/api/pith-number/IWXVDN5LE3OV3H5X3GP66SU53G/graph.json","fetch_events":"https://pith.science/api/pith-number/IWXVDN5LE3OV3H5X3GP66SU53G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G/action/storage_attestation","attest_author":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G/action/author_attestation","sign_citation":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G/action/citation_signature","submit_replication":"https://pith.science/pith/IWXVDN5LE3OV3H5X3GP66SU53G/action/replication_record"}},"created_at":"2026-07-05T08:38:47.594235+00:00","updated_at":"2026-07-05T08:38:47.594235+00:00"}