{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ILATG7HMWBNRWSW657CV3YLVAB","short_pith_number":"pith:ILATG7HM","canonical_record":{"source":{"id":"2402.04627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-07T07:24:01Z","cross_cats_sorted":["cs.CL","cs.DB","cs.IR"],"title_canon_sha256":"dbf3f29ee2dfb331139fb23045f4e8ac4f690a477a5c1a4935cb6da8fcd8b364","abstract_canon_sha256":"943f278c64ce04688c7db4607504072bf112608ec1b7aff6e60ebfb58a058dd8"},"schema_version":"1.0"},"canonical_sha256":"42c1337cecb05b1b4adeefc55de175005659540ff7d9350d9f4334c7cc65f1b2","source":{"kind":"arxiv","id":"2402.04627","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04627","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04627v1","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04627","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"ILATG7HMWBNR","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"ILATG7HMWBNRWSW6","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"ILATG7HM","created_at":"2026-07-05T11:58:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ILATG7HMWBNRWSW657CV3YLVAB","target":"record","payload":{"canonical_record":{"source":{"id":"2402.04627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-07T07:24:01Z","cross_cats_sorted":["cs.CL","cs.DB","cs.IR"],"title_canon_sha256":"dbf3f29ee2dfb331139fb23045f4e8ac4f690a477a5c1a4935cb6da8fcd8b364","abstract_canon_sha256":"943f278c64ce04688c7db4607504072bf112608ec1b7aff6e60ebfb58a058dd8"},"schema_version":"1.0"},"canonical_sha256":"42c1337cecb05b1b4adeefc55de175005659540ff7d9350d9f4334c7cc65f1b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:17.432603Z","signature_b64":"YPikuCfGtHm7EZaj+ltTOyuNrUQnBqquX+A9WXr2Km3l8NeCivDYBg9kMGSr02L8qpv8SqUHzYxc3mDYE6bSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42c1337cecb05b1b4adeefc55de175005659540ff7d9350d9f4334c7cc65f1b2","last_reissued_at":"2026-07-05T11:58:17.432174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:17.432174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.04627","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:58:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FyVuBp45/Vci5M412Z9NgJa0waBdsGhNZHRBeRLswrCFOFTsFoEWNVkVD0qxQCjJipr6U+Zz/WZXOfeijF86Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:11:14.287386Z"},"content_sha256":"ce3d34b97388939b877399b5fd71e300ae4d1562a283680637c0a62038a65e5c","schema_version":"1.0","event_id":"sha256:ce3d34b97388939b877399b5fd71e300ae4d1562a283680637c0a62038a65e5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ILATG7HMWBNRWSW657CV3YLVAB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over a Life Science Knowledge Graph","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","cs.DB","cs.IR"],"primary_cat":"cs.AI","authors_text":"Ana Claudia Sima, Julio C. Rangel, Norio Kobayashi, Tarcisio Mendes de Farias","submitted_at":"2024-02-07T07:24:01Z","abstract_excerpt":"The recent success of Large Language Models (LLM) in a wide range of Natural Language Processing applications opens the path towards novel Question Answering Systems over Knowledge Graphs leveraging LLMs. However, one of the main obstacles preventing their implementation is the scarcity of training data for the task of translating questions into corresponding SPARQL queries, particularly in the case of domain-specific KGs. To overcome this challenge, in this study, we evaluate several strategies for fine-tuning the OpenLlama LLM for question answering over life science knowledge graphs. In par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04627","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/2402.04627/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:58:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVeH+nZ71P7w8DWyVN5zA4i26sS7hQ/tTf5Kcskb4AGhNy69IWEBByv4mbtOghYzPnE+8N7P5zS/aH/mTj+KCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:11:14.291976Z"},"content_sha256":"3c61fd035a74727941b40093d8da1f3c7f5e0e4a512cfa1a916935e2a28aead1","schema_version":"1.0","event_id":"sha256:3c61fd035a74727941b40093d8da1f3c7f5e0e4a512cfa1a916935e2a28aead1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ILATG7HMWBNRWSW657CV3YLVAB/bundle.json","state_url":"https://pith.science/pith/ILATG7HMWBNRWSW657CV3YLVAB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ILATG7HMWBNRWSW657CV3YLVAB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:11:14Z","links":{"resolver":"https://pith.science/pith/ILATG7HMWBNRWSW657CV3YLVAB","bundle":"https://pith.science/pith/ILATG7HMWBNRWSW657CV3YLVAB/bundle.json","state":"https://pith.science/pith/ILATG7HMWBNRWSW657CV3YLVAB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ILATG7HMWBNRWSW657CV3YLVAB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ILATG7HMWBNRWSW657CV3YLVAB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"943f278c64ce04688c7db4607504072bf112608ec1b7aff6e60ebfb58a058dd8","cross_cats_sorted":["cs.CL","cs.DB","cs.IR"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-07T07:24:01Z","title_canon_sha256":"dbf3f29ee2dfb331139fb23045f4e8ac4f690a477a5c1a4935cb6da8fcd8b364"},"schema_version":"1.0","source":{"id":"2402.04627","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04627","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04627v1","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04627","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"ILATG7HMWBNR","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"ILATG7HMWBNRWSW6","created_at":"2026-07-05T11:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"ILATG7HM","created_at":"2026-07-05T11:58:17Z"}],"graph_snapshots":[{"event_id":"sha256:3c61fd035a74727941b40093d8da1f3c7f5e0e4a512cfa1a916935e2a28aead1","target":"graph","created_at":"2026-07-05T11:58:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.04627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of Large Language Models (LLM) in a wide range of Natural Language Processing applications opens the path towards novel Question Answering Systems over Knowledge Graphs leveraging LLMs. However, one of the main obstacles preventing their implementation is the scarcity of training data for the task of translating questions into corresponding SPARQL queries, particularly in the case of domain-specific KGs. To overcome this challenge, in this study, we evaluate several strategies for fine-tuning the OpenLlama LLM for question answering over life science knowledge graphs. In par","authors_text":"Ana Claudia Sima, Julio C. Rangel, Norio Kobayashi, Tarcisio Mendes de Farias","cross_cats":["cs.CL","cs.DB","cs.IR"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-07T07:24:01Z","title":"SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over a Life Science Knowledge Graph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04627","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ce3d34b97388939b877399b5fd71e300ae4d1562a283680637c0a62038a65e5c","target":"record","created_at":"2026-07-05T11:58:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"943f278c64ce04688c7db4607504072bf112608ec1b7aff6e60ebfb58a058dd8","cross_cats_sorted":["cs.CL","cs.DB","cs.IR"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-07T07:24:01Z","title_canon_sha256":"dbf3f29ee2dfb331139fb23045f4e8ac4f690a477a5c1a4935cb6da8fcd8b364"},"schema_version":"1.0","source":{"id":"2402.04627","kind":"arxiv","version":1}},"canonical_sha256":"42c1337cecb05b1b4adeefc55de175005659540ff7d9350d9f4334c7cc65f1b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42c1337cecb05b1b4adeefc55de175005659540ff7d9350d9f4334c7cc65f1b2","first_computed_at":"2026-07-05T11:58:17.432174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:17.432174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YPikuCfGtHm7EZaj+ltTOyuNrUQnBqquX+A9WXr2Km3l8NeCivDYBg9kMGSr02L8qpv8SqUHzYxc3mDYE6bSDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:17.432603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04627","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce3d34b97388939b877399b5fd71e300ae4d1562a283680637c0a62038a65e5c","sha256:3c61fd035a74727941b40093d8da1f3c7f5e0e4a512cfa1a916935e2a28aead1"],"state_sha256":"d3c73eb4063bdb5e3534fc7019d3b1062f2ef58a6894979b8e9b1201ca98f5dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X0XCQC6mylLySmq7erKM6S4/sDe+4u/C6CW8U92gtiMImbbdaFBVgX2mt7dD3cSXHB0cYCurJ17KH7eOmhpZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:11:14.312385Z","bundle_sha256":"0a0c291d12d63b63c5734a505554940417f5f0e9cd4055173d59b6cc186b5b35"}}