{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SVHNGYVOLG3BPWLN36IJBSFNLF","short_pith_number":"pith:SVHNGYVO","schema_version":"1.0","canonical_sha256":"954ed362ae59b617d96ddf9090c8ad597ee0d07a745ab36d49b06f77961710b8","source":{"kind":"arxiv","id":"2201.05793","version":1},"attestation_state":"computed","paper":{"title":"A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Achille Fokoue, Alexander Gray, Cezar Pendus, Dinesh Garg, Dinesh Khandelwal, Francois Luus, G P Shrivatsa Bhargav, Guilherme Lima, Hima Karanam, Ibrahim Abdelaziz, L Venkata Subramaniam, Maria Chang, Nandana Mihindukulasooriya, Pavan Kapanipathi, Rosario Uceda-Sosa, Ryan Riegel, Sairam Gurajada, Salim Roukos, Santosh Srivastava, Saswati Dana, Shajith Ikbal, Srinivas Ravishankar, Sumit Neelam, Udit Sharma, Young-Suk Lee","submitted_at":"2022-01-15T08:49:09Z","abstract_excerpt":"Knowledge Base Question Answering (KBQA) tasks that involve complex reasoning are emerging as an important research direction. However, most existing KBQA datasets focus primarily on generic multi-hop reasoning over explicit facts, largely ignoring other reasoning types such as temporal, spatial, and taxonomic reasoning. In this paper, we present a benchmark dataset for temporal reasoning, TempQA-WD, to encourage research in extending the present approaches to target a more challenging set of complex reasoning tasks. Specifically, our benchmark is a temporal question answering dataset with the"},"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":"2201.05793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-15T08:49:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"221bfaf40d032e998a820e834b836c51a8b970c070facf1f531a58add2e513e3","abstract_canon_sha256":"1c6dec283b42ec6f4886c5b40e66b3761313cd26f90114852dd06387a8965515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:51.720362Z","signature_b64":"8+qi6lE1RzzCyzOr1CANNJ8ThHdCWm0zCUN/ZcqX0tEeGdSi7J5lPUuN9wcxRoTxzVejIpTQ+fWQL9ULcXvsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"954ed362ae59b617d96ddf9090c8ad597ee0d07a745ab36d49b06f77961710b8","last_reissued_at":"2026-07-05T03:48:51.719823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:51.719823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Achille Fokoue, Alexander Gray, Cezar Pendus, Dinesh Garg, Dinesh Khandelwal, Francois Luus, G P Shrivatsa Bhargav, Guilherme Lima, Hima Karanam, Ibrahim Abdelaziz, L Venkata Subramaniam, Maria Chang, Nandana Mihindukulasooriya, Pavan Kapanipathi, Rosario Uceda-Sosa, Ryan Riegel, Sairam Gurajada, Salim Roukos, Santosh Srivastava, Saswati Dana, Shajith Ikbal, Srinivas Ravishankar, Sumit Neelam, Udit Sharma, Young-Suk Lee","submitted_at":"2022-01-15T08:49:09Z","abstract_excerpt":"Knowledge Base Question Answering (KBQA) tasks that involve complex reasoning are emerging as an important research direction. However, most existing KBQA datasets focus primarily on generic multi-hop reasoning over explicit facts, largely ignoring other reasoning types such as temporal, spatial, and taxonomic reasoning. In this paper, we present a benchmark dataset for temporal reasoning, TempQA-WD, to encourage research in extending the present approaches to target a more challenging set of complex reasoning tasks. Specifically, our benchmark is a temporal question answering dataset with the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05793","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/2201.05793/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":"2201.05793","created_at":"2026-07-05T03:48:51.719879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05793v1","created_at":"2026-07-05T03:48:51.719879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05793","created_at":"2026-07-05T03:48:51.719879+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVHNGYVOLG3B","created_at":"2026-07-05T03:48:51.719879+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVHNGYVOLG3BPWLN","created_at":"2026-07-05T03:48:51.719879+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVHNGYVO","created_at":"2026-07-05T03:48:51.719879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05746","citing_title":"LLM-Symbolic Integration for Robust Temporal Tabular Reasoning","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF","json":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF.json","graph_json":"https://pith.science/api/pith-number/SVHNGYVOLG3BPWLN36IJBSFNLF/graph.json","events_json":"https://pith.science/api/pith-number/SVHNGYVOLG3BPWLN36IJBSFNLF/events.json","paper":"https://pith.science/paper/SVHNGYVO"},"agent_actions":{"view_html":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF","download_json":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF.json","view_paper":"https://pith.science/paper/SVHNGYVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05793&json=true","fetch_graph":"https://pith.science/api/pith-number/SVHNGYVOLG3BPWLN36IJBSFNLF/graph.json","fetch_events":"https://pith.science/api/pith-number/SVHNGYVOLG3BPWLN36IJBSFNLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF/action/storage_attestation","attest_author":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF/action/author_attestation","sign_citation":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF/action/citation_signature","submit_replication":"https://pith.science/pith/SVHNGYVOLG3BPWLN36IJBSFNLF/action/replication_record"}},"created_at":"2026-07-05T03:48:51.719879+00:00","updated_at":"2026-07-05T03:48:51.719879+00:00"}