{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7R3PEJFVXHBQ3W7S7AIXS2CL7T","short_pith_number":"pith:7R3PEJFV","schema_version":"1.0","canonical_sha256":"fc76f224b5b9c30ddbf2f81179684bfcece4968e19148433b7f4232e472d58e5","source":{"kind":"arxiv","id":"2410.09428","version":1},"attestation_state":"computed","paper":{"title":"Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jan Hadl, Johannes Oetsch, Nelson Higuera, Thomas Eiter","submitted_at":"2024-10-12T08:17:03Z","abstract_excerpt":"Visual Question Answering (VQA) is the task of answering a question about an image and requires processing multimodal input and reasoning to obtain the answer. Modular solutions that use declarative representations within the reasoning component have a clear advantage over end-to-end trained systems regarding interpretability. The downside is that crafting the rules for such a component can be an additional burden on the developer. We address this challenge by presenting an approach for declarative knowledge distillation from Large Language Models (LLMs). Our method is to prompt an LLM to exte"},"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":"2410.09428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-12T08:17:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5d235671eecd839b9796da07b8c9eeada545c28cf7cea76b60e22fba288bf137","abstract_canon_sha256":"d49929b26e6b4f0e63c3e3839c0a2d9c7199d26645160c5deccf126613ea76fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:05.806769Z","signature_b64":"pLd/W8AhOYS1MNN+YoApFEXksMsZfcp3clzqSy8pz/lVTJhgl5dsg6CSlNYtp85fUOng78PF0lkdJV+WDdenDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc76f224b5b9c30ddbf2f81179684bfcece4968e19148433b7f4232e472d58e5","last_reissued_at":"2026-07-05T09:20:05.806306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:05.806306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jan Hadl, Johannes Oetsch, Nelson Higuera, Thomas Eiter","submitted_at":"2024-10-12T08:17:03Z","abstract_excerpt":"Visual Question Answering (VQA) is the task of answering a question about an image and requires processing multimodal input and reasoning to obtain the answer. Modular solutions that use declarative representations within the reasoning component have a clear advantage over end-to-end trained systems regarding interpretability. The downside is that crafting the rules for such a component can be an additional burden on the developer. We address this challenge by presenting an approach for declarative knowledge distillation from Large Language Models (LLMs). Our method is to prompt an LLM to exte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09428","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/2410.09428/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":"2410.09428","created_at":"2026-07-05T09:20:05.806373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09428v1","created_at":"2026-07-05T09:20:05.806373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09428","created_at":"2026-07-05T09:20:05.806373+00:00"},{"alias_kind":"pith_short_12","alias_value":"7R3PEJFVXHBQ","created_at":"2026-07-05T09:20:05.806373+00:00"},{"alias_kind":"pith_short_16","alias_value":"7R3PEJFVXHBQ3W7S","created_at":"2026-07-05T09:20:05.806373+00:00"},{"alias_kind":"pith_short_8","alias_value":"7R3PEJFV","created_at":"2026-07-05T09:20:05.806373+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/7R3PEJFVXHBQ3W7S7AIXS2CL7T","json":"https://pith.science/pith/7R3PEJFVXHBQ3W7S7AIXS2CL7T.json","graph_json":"https://pith.science/api/pith-number/7R3PEJFVXHBQ3W7S7AIXS2CL7T/graph.json","events_json":"https://pith.science/api/pith-number/7R3PEJFVXHBQ3W7S7AIXS2CL7T/events.json","paper":"https://pith.science/paper/7R3PEJFV"},"agent_actions":{"view_html":"https://pith.science/pith/7R3PEJFVXHBQ3W7S7AIXS2CL7T","download_json":"https://pith.science/pith/7R3PEJFVXHBQ3W7S7AIXS2CL7T.json","view_paper":"https://pith.science/paper/7R3PEJFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09428&json=true","fetch_graph":"https://pith.science/api/pith-number/7R3PEJFVXHBQ3W7S7AIXS2CL7T/graph.json","fetch_events":"https://pith.science/api/pith-number/7R3PEJFVXHBQ3W7S7AIXS2CL7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7R3PEJFVXHBQ3W7S7AIXS2CL7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7R3PEJFVXHBQ3W7S7AIXS2CL7T/action/storage_attestation","attest_author":"https://pith.science/pith/7R3PEJFVXHBQ3W7S7AIXS2CL7T/action/author_attestation","sign_citation":"https://pith.science/pith/7R3PEJFVXHBQ3W7S7AIXS2CL7T/action/citation_signature","submit_replication":"https://pith.science/pith/7R3PEJFVXHBQ3W7S7AIXS2CL7T/action/replication_record"}},"created_at":"2026-07-05T09:20:05.806373+00:00","updated_at":"2026-07-05T09:20:05.806373+00:00"}