{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:25LT2T2KN6MLAWON7ZRK33PY6M","short_pith_number":"pith:25LT2T2K","schema_version":"1.0","canonical_sha256":"d7573d4f4a6f98b059cdfe62adedf8f3065286a6233c979a6f19a9b27fdfe427","source":{"kind":"arxiv","id":"2507.17178","version":3},"attestation_state":"computed","paper":{"title":"SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Enpei Niu, Huajun Chen, Lei Liang, Mengshu Sun, Wen Zhang, Yin Hua, Zhiqiang Liu","submitted_at":"2025-07-23T03:52:24Z","abstract_excerpt":"Although large language models (LLMs) have made significant progress in understanding Structured Knowledge (SK) like KG and Table, existing evaluations for SK understanding are non-rigorous (i.e., lacking evaluations of specific capabilities) and focus on a single type of SK. Therefore, we aim to propose a more comprehensive and rigorous structured knowledge understanding benchmark to diagnose the shortcomings of LLMs. In this paper, we introduce SKA-Bench, a Structured Knowledge Augmented QA Benchmark that encompasses four widely used structured knowledge forms: KG, Table, KG+Text, and Table+"},"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":"2507.17178","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T03:52:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8561829980ea51d5860668b7625914f36a475d6005a8c1c09d6931125d5bcf7","abstract_canon_sha256":"d6f6c15a4924d03e2f82b3d8068081a292f28bbdee35bae4b89747fb7c5dd69b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:25.039017Z","signature_b64":"jlauqvDmviSOGZ4LtcaIKKnotM3ZoCEKeyLnFGrnihA+1h9MukIOc2tHJ+7Syh7xQ5tn0Es806URPKtKUo/fCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7573d4f4a6f98b059cdfe62adedf8f3065286a6233c979a6f19a9b27fdfe427","last_reissued_at":"2026-07-05T12:01:25.038535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:25.038535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Enpei Niu, Huajun Chen, Lei Liang, Mengshu Sun, Wen Zhang, Yin Hua, Zhiqiang Liu","submitted_at":"2025-07-23T03:52:24Z","abstract_excerpt":"Although large language models (LLMs) have made significant progress in understanding Structured Knowledge (SK) like KG and Table, existing evaluations for SK understanding are non-rigorous (i.e., lacking evaluations of specific capabilities) and focus on a single type of SK. Therefore, we aim to propose a more comprehensive and rigorous structured knowledge understanding benchmark to diagnose the shortcomings of LLMs. In this paper, we introduce SKA-Bench, a Structured Knowledge Augmented QA Benchmark that encompasses four widely used structured knowledge forms: KG, Table, KG+Text, and Table+"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17178","kind":"arxiv","version":3},"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/2507.17178/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":"2507.17178","created_at":"2026-07-05T12:01:25.038606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17178v3","created_at":"2026-07-05T12:01:25.038606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17178","created_at":"2026-07-05T12:01:25.038606+00:00"},{"alias_kind":"pith_short_12","alias_value":"25LT2T2KN6ML","created_at":"2026-07-05T12:01:25.038606+00:00"},{"alias_kind":"pith_short_16","alias_value":"25LT2T2KN6MLAWON","created_at":"2026-07-05T12:01:25.038606+00:00"},{"alias_kind":"pith_short_8","alias_value":"25LT2T2K","created_at":"2026-07-05T12:01:25.038606+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/25LT2T2KN6MLAWON7ZRK33PY6M","json":"https://pith.science/pith/25LT2T2KN6MLAWON7ZRK33PY6M.json","graph_json":"https://pith.science/api/pith-number/25LT2T2KN6MLAWON7ZRK33PY6M/graph.json","events_json":"https://pith.science/api/pith-number/25LT2T2KN6MLAWON7ZRK33PY6M/events.json","paper":"https://pith.science/paper/25LT2T2K"},"agent_actions":{"view_html":"https://pith.science/pith/25LT2T2KN6MLAWON7ZRK33PY6M","download_json":"https://pith.science/pith/25LT2T2KN6MLAWON7ZRK33PY6M.json","view_paper":"https://pith.science/paper/25LT2T2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17178&json=true","fetch_graph":"https://pith.science/api/pith-number/25LT2T2KN6MLAWON7ZRK33PY6M/graph.json","fetch_events":"https://pith.science/api/pith-number/25LT2T2KN6MLAWON7ZRK33PY6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25LT2T2KN6MLAWON7ZRK33PY6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25LT2T2KN6MLAWON7ZRK33PY6M/action/storage_attestation","attest_author":"https://pith.science/pith/25LT2T2KN6MLAWON7ZRK33PY6M/action/author_attestation","sign_citation":"https://pith.science/pith/25LT2T2KN6MLAWON7ZRK33PY6M/action/citation_signature","submit_replication":"https://pith.science/pith/25LT2T2KN6MLAWON7ZRK33PY6M/action/replication_record"}},"created_at":"2026-07-05T12:01:25.038606+00:00","updated_at":"2026-07-05T12:01:25.038606+00:00"}