{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FMR4WDLMDAQB4KN3VPROJMCGRA","short_pith_number":"pith:FMR4WDLM","schema_version":"1.0","canonical_sha256":"2b23cb0d6c18201e29bbabe2e4b04688125b87b77e44e466260cc77deb2be99c","source":{"kind":"arxiv","id":"2503.00912","version":1},"attestation_state":"computed","paper":{"title":"HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Li, Jiancheng Tu, Pangjing Wu, Peter H.F. Ng, Peter Q. Chen, Qing Li, Xu Yuan, Ye Jia, Zhuohang Jiang, Ziran Liang","submitted_at":"2025-03-02T14:25:37Z","abstract_excerpt":"Structure reasoning is a fundamental capability of large language models (LLMs), enabling them to reason about structured commonsense and answer multi-hop questions. However, existing benchmarks for structure reasoning mainly focus on horizontal and coordinate structures (\\emph{e.g.} graphs), overlooking the hierarchical relationships within them. Hierarchical structure reasoning is crucial for human cognition, particularly in memory organization and problem-solving. It also plays a key role in various real-world tasks, such as information extraction and decision-making. To address this gap, w"},"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":"2503.00912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T14:25:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"12d1dcf09679f59f74761af2412a56d2a64c14a3af4242548175af11c83f272a","abstract_canon_sha256":"06bcfc68f4537f4280785ef341065880c9a0ccbebeb2cdbc97a61509ad6de244"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:32.344966Z","signature_b64":"jkd31GjLiCUi8RRjaSVlWryB8FdP586hIlXXmsl5m/X7zZ1hlUpi6m2c7gSXdjsc0uH8qpJyou1ueuQE0vCeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b23cb0d6c18201e29bbabe2e4b04688125b87b77e44e466260cc77deb2be99c","last_reissued_at":"2026-07-05T10:22:32.344522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:32.344522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Li, Jiancheng Tu, Pangjing Wu, Peter H.F. Ng, Peter Q. Chen, Qing Li, Xu Yuan, Ye Jia, Zhuohang Jiang, Ziran Liang","submitted_at":"2025-03-02T14:25:37Z","abstract_excerpt":"Structure reasoning is a fundamental capability of large language models (LLMs), enabling them to reason about structured commonsense and answer multi-hop questions. However, existing benchmarks for structure reasoning mainly focus on horizontal and coordinate structures (\\emph{e.g.} graphs), overlooking the hierarchical relationships within them. Hierarchical structure reasoning is crucial for human cognition, particularly in memory organization and problem-solving. It also plays a key role in various real-world tasks, such as information extraction and decision-making. To address this gap, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00912","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/2503.00912/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":"2503.00912","created_at":"2026-07-05T10:22:32.344591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00912v1","created_at":"2026-07-05T10:22:32.344591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00912","created_at":"2026-07-05T10:22:32.344591+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMR4WDLMDAQB","created_at":"2026-07-05T10:22:32.344591+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMR4WDLMDAQB4KN3","created_at":"2026-07-05T10:22:32.344591+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMR4WDLM","created_at":"2026-07-05T10:22:32.344591+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23678","citing_title":"Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA","json":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA.json","graph_json":"https://pith.science/api/pith-number/FMR4WDLMDAQB4KN3VPROJMCGRA/graph.json","events_json":"https://pith.science/api/pith-number/FMR4WDLMDAQB4KN3VPROJMCGRA/events.json","paper":"https://pith.science/paper/FMR4WDLM"},"agent_actions":{"view_html":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA","download_json":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA.json","view_paper":"https://pith.science/paper/FMR4WDLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00912&json=true","fetch_graph":"https://pith.science/api/pith-number/FMR4WDLMDAQB4KN3VPROJMCGRA/graph.json","fetch_events":"https://pith.science/api/pith-number/FMR4WDLMDAQB4KN3VPROJMCGRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA/action/storage_attestation","attest_author":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA/action/author_attestation","sign_citation":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA/action/citation_signature","submit_replication":"https://pith.science/pith/FMR4WDLMDAQB4KN3VPROJMCGRA/action/replication_record"}},"created_at":"2026-07-05T10:22:32.344591+00:00","updated_at":"2026-07-05T10:22:32.344591+00:00"}