{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FTBWZ6SJNGY5TS6WBJBTSJUW6G","short_pith_number":"pith:FTBWZ6SJ","schema_version":"1.0","canonical_sha256":"2cc36cfa4969b1d9cbd60a43392696f18d2cdc49ec2f605e937195ff435f96c2","source":{"kind":"arxiv","id":"2204.08753","version":1},"attestation_state":"computed","paper":{"title":"Table-based Fact Verification with Self-adaptive Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ji Wu, Kaiyin Zhou, Xien Liu, Yuxuan Zhou","submitted_at":"2022-04-19T08:47:39Z","abstract_excerpt":"The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem. It inherently requires informative reasoning over natural language together with different numerical and logical reasoning on tables (e.g., count, superlative, comparative). Considering that, we exploit mixture-of-experts and present in this paper a new method: Self-adaptive Mixture-of-Experts Network (SaMoE). Specifically, we have developed a mixture-of-experts neural network to recognize and execute different types of reasoning -- the network is composed of multip"},"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":"2204.08753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-04-19T08:47:39Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"ab273ad6f320759ac48fd0d84ae0908359534dcf209c651972c8e43ac5bc730c","abstract_canon_sha256":"76ac20c7cd02ec412bfbdf90264fae61535bd1b37974ddd9de9b1d4815205581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:33.748179Z","signature_b64":"zmXrA0WdvBjqCRF91PooRdOEYelOGwJVqm7M2nDOTvLF583n9As2iJpiV/glqET52vKGFpgLTSYZDipIztRjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cc36cfa4969b1d9cbd60a43392696f18d2cdc49ec2f605e937195ff435f96c2","last_reissued_at":"2026-07-05T04:15:33.747731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:33.747731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Table-based Fact Verification with Self-adaptive Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ji Wu, Kaiyin Zhou, Xien Liu, Yuxuan Zhou","submitted_at":"2022-04-19T08:47:39Z","abstract_excerpt":"The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem. It inherently requires informative reasoning over natural language together with different numerical and logical reasoning on tables (e.g., count, superlative, comparative). Considering that, we exploit mixture-of-experts and present in this paper a new method: Self-adaptive Mixture-of-Experts Network (SaMoE). Specifically, we have developed a mixture-of-experts neural network to recognize and execute different types of reasoning -- the network is composed of multip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08753","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/2204.08753/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":"2204.08753","created_at":"2026-07-05T04:15:33.747809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08753v1","created_at":"2026-07-05T04:15:33.747809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08753","created_at":"2026-07-05T04:15:33.747809+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTBWZ6SJNGY5","created_at":"2026-07-05T04:15:33.747809+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTBWZ6SJNGY5TS6W","created_at":"2026-07-05T04:15:33.747809+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTBWZ6SJ","created_at":"2026-07-05T04:15:33.747809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12430","citing_title":"SCFCRC: Simultaneously Counteract Feature Camouflage and Relation Camouflage for Fraud Detection","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G","json":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G.json","graph_json":"https://pith.science/api/pith-number/FTBWZ6SJNGY5TS6WBJBTSJUW6G/graph.json","events_json":"https://pith.science/api/pith-number/FTBWZ6SJNGY5TS6WBJBTSJUW6G/events.json","paper":"https://pith.science/paper/FTBWZ6SJ"},"agent_actions":{"view_html":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G","download_json":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G.json","view_paper":"https://pith.science/paper/FTBWZ6SJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08753&json=true","fetch_graph":"https://pith.science/api/pith-number/FTBWZ6SJNGY5TS6WBJBTSJUW6G/graph.json","fetch_events":"https://pith.science/api/pith-number/FTBWZ6SJNGY5TS6WBJBTSJUW6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G/action/storage_attestation","attest_author":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G/action/author_attestation","sign_citation":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G/action/citation_signature","submit_replication":"https://pith.science/pith/FTBWZ6SJNGY5TS6WBJBTSJUW6G/action/replication_record"}},"created_at":"2026-07-05T04:15:33.747809+00:00","updated_at":"2026-07-05T04:15:33.747809+00:00"}