{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2F7OE2U7K6YCCL2CU5E7K74EB7","short_pith_number":"pith:2F7OE2U7","schema_version":"1.0","canonical_sha256":"d17ee26a9f57b0212f42a749f57f840fe5c05aa6a7b5ab32f7074e3d0223245c","source":{"kind":"arxiv","id":"2109.13430","version":1},"attestation_state":"computed","paper":{"title":"SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases","license":"http://creativecommons.org/licenses/by/4.0/","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 LimaRyan Riegel, Hima Karanam, Ibrahim Abdelaziz, L Venkata Subramaniam, Maria Chang, Nandana Mihindukulasooriya, Pavan Kapanipathi, Rosario Uceda-Sosa, Sairam Gurajada, Salim Roukos, Santosh Srivastava, Saswati Dana, Shajith Ikbal, Srinivas Ravishankar, Sumit Neelam, Udit Sharma, Young-Suk Lee","submitted_at":"2021-09-28T01:57:56Z","abstract_excerpt":"Knowledge Base Question Answering (KBQA) tasks that in-volve complex reasoning are emerging as an important re-search direction. However, most KBQA systems struggle withgeneralizability, particularly on two dimensions: (a) acrossmultiple reasoning types where both datasets and systems haveprimarily focused on multi-hop reasoning, and (b) across mul-tiple knowledge bases, where KBQA approaches are specif-ically tuned to a single knowledge base. In this paper, wepresent SYGMA, a modular approach facilitating general-izability across multiple knowledge bases and multiple rea-soning types. Specifi"},"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":"2109.13430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-28T01:57:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67dec72e95915fc1d2ea3b538ba5b0b015ccc163236d4a53be369c33e8af9e1f","abstract_canon_sha256":"76190e6a62adebd96d1459c56ca3052d5fd0bb5b09c6c3183fd7ae91075400cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:02.678306Z","signature_b64":"aegaYy3ZUJagsik880rzEbDxa2jh3Cit6KyDsU7gtrkOm9bZeCzDKuosOA/3l/Yh884jPoy1x9W13KSH8ZLaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17ee26a9f57b0212f42a749f57f840fe5c05aa6a7b5ab32f7074e3d0223245c","last_reissued_at":"2026-07-05T03:18:02.677829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:02.677829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases","license":"http://creativecommons.org/licenses/by/4.0/","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 LimaRyan Riegel, Hima Karanam, Ibrahim Abdelaziz, L Venkata Subramaniam, Maria Chang, Nandana Mihindukulasooriya, Pavan Kapanipathi, Rosario Uceda-Sosa, Sairam Gurajada, Salim Roukos, Santosh Srivastava, Saswati Dana, Shajith Ikbal, Srinivas Ravishankar, Sumit Neelam, Udit Sharma, Young-Suk Lee","submitted_at":"2021-09-28T01:57:56Z","abstract_excerpt":"Knowledge Base Question Answering (KBQA) tasks that in-volve complex reasoning are emerging as an important re-search direction. However, most KBQA systems struggle withgeneralizability, particularly on two dimensions: (a) acrossmultiple reasoning types where both datasets and systems haveprimarily focused on multi-hop reasoning, and (b) across mul-tiple knowledge bases, where KBQA approaches are specif-ically tuned to a single knowledge base. In this paper, wepresent SYGMA, a modular approach facilitating general-izability across multiple knowledge bases and multiple rea-soning types. Specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13430","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/2109.13430/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":"2109.13430","created_at":"2026-07-05T03:18:02.677889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.13430v1","created_at":"2026-07-05T03:18:02.677889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13430","created_at":"2026-07-05T03:18:02.677889+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F7OE2U7K6YC","created_at":"2026-07-05T03:18:02.677889+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F7OE2U7K6YCCL2C","created_at":"2026-07-05T03:18:02.677889+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F7OE2U7","created_at":"2026-07-05T03:18:02.677889+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.18296","citing_title":"Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7","json":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7.json","graph_json":"https://pith.science/api/pith-number/2F7OE2U7K6YCCL2CU5E7K74EB7/graph.json","events_json":"https://pith.science/api/pith-number/2F7OE2U7K6YCCL2CU5E7K74EB7/events.json","paper":"https://pith.science/paper/2F7OE2U7"},"agent_actions":{"view_html":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7","download_json":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7.json","view_paper":"https://pith.science/paper/2F7OE2U7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.13430&json=true","fetch_graph":"https://pith.science/api/pith-number/2F7OE2U7K6YCCL2CU5E7K74EB7/graph.json","fetch_events":"https://pith.science/api/pith-number/2F7OE2U7K6YCCL2CU5E7K74EB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7/action/storage_attestation","attest_author":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7/action/author_attestation","sign_citation":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7/action/citation_signature","submit_replication":"https://pith.science/pith/2F7OE2U7K6YCCL2CU5E7K74EB7/action/replication_record"}},"created_at":"2026-07-05T03:18:02.677889+00:00","updated_at":"2026-07-05T03:18:02.677889+00:00"}