{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IH5T67E3ZF4RDE4POBREQUPZLL","short_pith_number":"pith:IH5T67E3","schema_version":"1.0","canonical_sha256":"41fb3f7c9bc97911938f70624851f95ac54921eda50c4f4a99703582cefa0073","source":{"kind":"arxiv","id":"2608.01684","version":1},"attestation_state":"computed","paper":{"title":"GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Yang, Chuan Shi, Jiarui Tan, Jiawei Liu, Muhan Zhang, Yabo Guo, Yujie Xing, Zhongjian Zhang","submitted_at":"2026-08-03T04:18:31Z","abstract_excerpt":"Large language model (LLM) agents are increasingly capable of planning, using tools, and interacting with external environments. They are typically supported by harnesses, which manage state and coordinate multi-step execution. Graph analysis provides a promising setting for evaluating their agentic capabilities, because it requires agents to access data and execute operations in a graph environment. However, existing graph benchmarks for LLMs provide limited coverage of graph tasks and graph types, making it difficult to comprehensively evaluate LLM agents. Moreover, they typically formulate "},"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":"2608.01684","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T04:18:31Z","cross_cats_sorted":[],"title_canon_sha256":"f649399a1fe00724881359924f06bac04d6522a665e9dc592778abe02d2d03b9","abstract_canon_sha256":"a9519753d843ea6d0b3428c96b9ef4a8acb7f360b434fc46234417566693d1d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:06:24.558898Z","signature_b64":"KvBelrxH4UDvAoWAt6LttWg2ZFobNlwU7sJTlbOIQHDJN4eU85GlJz96TzGTYiZ9pfB/wrvBhaZ8fJvh8az/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41fb3f7c9bc97911938f70624851f95ac54921eda50c4f4a99703582cefa0073","last_reissued_at":"2026-08-04T02:06:24.557319Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:06:24.557319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Yang, Chuan Shi, Jiarui Tan, Jiawei Liu, Muhan Zhang, Yabo Guo, Yujie Xing, Zhongjian Zhang","submitted_at":"2026-08-03T04:18:31Z","abstract_excerpt":"Large language model (LLM) agents are increasingly capable of planning, using tools, and interacting with external environments. They are typically supported by harnesses, which manage state and coordinate multi-step execution. Graph analysis provides a promising setting for evaluating their agentic capabilities, because it requires agents to access data and execute operations in a graph environment. However, existing graph benchmarks for LLMs provide limited coverage of graph tasks and graph types, making it difficult to comprehensively evaluate LLM agents. Moreover, they typically formulate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01684","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/2608.01684/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":"2608.01684","created_at":"2026-08-04T02:06:24.558750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01684v1","created_at":"2026-08-04T02:06:24.558750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01684","created_at":"2026-08-04T02:06:24.558750+00:00"},{"alias_kind":"pith_short_12","alias_value":"IH5T67E3ZF4R","created_at":"2026-08-04T02:06:24.558750+00:00"},{"alias_kind":"pith_short_16","alias_value":"IH5T67E3ZF4RDE4P","created_at":"2026-08-04T02:06:24.558750+00:00"},{"alias_kind":"pith_short_8","alias_value":"IH5T67E3","created_at":"2026-08-04T02:06:24.558750+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/IH5T67E3ZF4RDE4POBREQUPZLL","json":"https://pith.science/pith/IH5T67E3ZF4RDE4POBREQUPZLL.json","graph_json":"https://pith.science/api/pith-number/IH5T67E3ZF4RDE4POBREQUPZLL/graph.json","events_json":"https://pith.science/api/pith-number/IH5T67E3ZF4RDE4POBREQUPZLL/events.json","paper":"https://pith.science/paper/IH5T67E3"},"agent_actions":{"view_html":"https://pith.science/pith/IH5T67E3ZF4RDE4POBREQUPZLL","download_json":"https://pith.science/pith/IH5T67E3ZF4RDE4POBREQUPZLL.json","view_paper":"https://pith.science/paper/IH5T67E3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01684&json=true","fetch_graph":"https://pith.science/api/pith-number/IH5T67E3ZF4RDE4POBREQUPZLL/graph.json","fetch_events":"https://pith.science/api/pith-number/IH5T67E3ZF4RDE4POBREQUPZLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IH5T67E3ZF4RDE4POBREQUPZLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IH5T67E3ZF4RDE4POBREQUPZLL/action/storage_attestation","attest_author":"https://pith.science/pith/IH5T67E3ZF4RDE4POBREQUPZLL/action/author_attestation","sign_citation":"https://pith.science/pith/IH5T67E3ZF4RDE4POBREQUPZLL/action/citation_signature","submit_replication":"https://pith.science/pith/IH5T67E3ZF4RDE4POBREQUPZLL/action/replication_record"}},"created_at":"2026-08-04T02:06:24.558750+00:00","updated_at":"2026-08-04T02:06:24.558750+00:00"}