{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YJM6X555NSGBIQX6DOE23FSSQJ","short_pith_number":"pith:YJM6X555","schema_version":"1.0","canonical_sha256":"c259ebf7bd6c8c1442fe1b89ad9652824445631f80e49ea4555ae77cf0b23c4a","source":{"kind":"arxiv","id":"2210.09162","version":1},"attestation_state":"computed","paper":{"title":"Table-To-Text generation and pre-training with TabT5","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ewa Andrejczuk, Francesco Piccinno, Julian Martin Eisenschlos, Syrine Krichene, Yasemin Altun","submitted_at":"2022-10-17T15:05:53Z","abstract_excerpt":"Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks such as cell selection or entailment detection. We present TABT5, an encoder-decoder model that generates natural language text based on tables and textual inputs. TABT5 overcomes the encoder-only limitation by incorporating a decoder component and leverages the input structure with table specific embeddings and pre-training. TABT5 achieves new state-of-the-ar"},"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":"2210.09162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-17T15:05:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04bd10ecddb711f8a2679e8d592f45fa167f557745f5414c363e880eaf2aeffe","abstract_canon_sha256":"0328ca78d0b4d3ea3d452de670a6f5abc6eb41ee134db7ae207d6e6e401f48ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:19.655888Z","signature_b64":"sHKEzo7tlnfpmkIqIMvBS2vbAu5ME9vh0PN0nJEDpczHZteBJxEMmmCgNiybZRf7GaCRWweoe7buOpS5E6vQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c259ebf7bd6c8c1442fe1b89ad9652824445631f80e49ea4555ae77cf0b23c4a","last_reissued_at":"2026-07-05T05:07:19.655466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:19.655466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Table-To-Text generation and pre-training with TabT5","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ewa Andrejczuk, Francesco Piccinno, Julian Martin Eisenschlos, Syrine Krichene, Yasemin Altun","submitted_at":"2022-10-17T15:05:53Z","abstract_excerpt":"Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks such as cell selection or entailment detection. We present TABT5, an encoder-decoder model that generates natural language text based on tables and textual inputs. TABT5 overcomes the encoder-only limitation by incorporating a decoder component and leverages the input structure with table specific embeddings and pre-training. TABT5 achieves new state-of-the-ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09162","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/2210.09162/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":"2210.09162","created_at":"2026-07-05T05:07:19.655538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09162v1","created_at":"2026-07-05T05:07:19.655538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09162","created_at":"2026-07-05T05:07:19.655538+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJM6X555NSGB","created_at":"2026-07-05T05:07:19.655538+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJM6X555NSGBIQX6","created_at":"2026-07-05T05:07:19.655538+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJM6X555","created_at":"2026-07-05T05:07:19.655538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09324","citing_title":"TEN: Table Explicitization, Neurosymbolically","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ","json":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ.json","graph_json":"https://pith.science/api/pith-number/YJM6X555NSGBIQX6DOE23FSSQJ/graph.json","events_json":"https://pith.science/api/pith-number/YJM6X555NSGBIQX6DOE23FSSQJ/events.json","paper":"https://pith.science/paper/YJM6X555"},"agent_actions":{"view_html":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ","download_json":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ.json","view_paper":"https://pith.science/paper/YJM6X555","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09162&json=true","fetch_graph":"https://pith.science/api/pith-number/YJM6X555NSGBIQX6DOE23FSSQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YJM6X555NSGBIQX6DOE23FSSQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ/action/storage_attestation","attest_author":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ/action/author_attestation","sign_citation":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ/action/citation_signature","submit_replication":"https://pith.science/pith/YJM6X555NSGBIQX6DOE23FSSQJ/action/replication_record"}},"created_at":"2026-07-05T05:07:19.655538+00:00","updated_at":"2026-07-05T05:07:19.655538+00:00"}