{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UASROSX4GDLJXNCRKE5HEOBECF","short_pith_number":"pith:UASROSX4","canonical_record":{"source":{"id":"2209.14812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-09-29T14:25:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cd8811c5a3a35ab34f607b952815f369bdcdbeeac3595e9f3390dcbc8625e3a2","abstract_canon_sha256":"f02428da2686a151ec1fcf4fa0938848c7760b9735b681f89aca50a1e884a1c7"},"schema_version":"1.0"},"canonical_sha256":"a025174afc30d69bb451513a7238241156cecd60839cdce6c8ea868974423d45","source":{"kind":"arxiv","id":"2209.14812","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14812","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14812v1","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14812","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"UASROSX4GDLJ","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"UASROSX4GDLJXNCR","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"UASROSX4","created_at":"2026-07-05T05:02:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UASROSX4GDLJXNCRKE5HEOBECF","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-09-29T14:25:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cd8811c5a3a35ab34f607b952815f369bdcdbeeac3595e9f3390dcbc8625e3a2","abstract_canon_sha256":"f02428da2686a151ec1fcf4fa0938848c7760b9735b681f89aca50a1e884a1c7"},"schema_version":"1.0"},"canonical_sha256":"a025174afc30d69bb451513a7238241156cecd60839cdce6c8ea868974423d45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:05.980025Z","signature_b64":"ZpjvIvoKv7PvhlgN2CSHsUkOyLwJyddfGhE6AG8vrR6x7iUWCfzQ30fLo1VjWhtzE1xc914UCuBAhvbiBJisAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a025174afc30d69bb451513a7238241156cecd60839cdce6c8ea868974423d45","last_reissued_at":"2026-07-05T05:02:05.979620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:05.979620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14812","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLeEZucgOaWLWwHM7nrvucwA7Su0AYBEwFVAaX00d7byccvZgi/DECgOy6k1u21Alt4UiAFvk9UTnKgM8xNRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:18:13.877874Z"},"content_sha256":"c1eea424124103b058dcd837280b178650d7b1e8d6bf0e71d550071db0608923","schema_version":"1.0","event_id":"sha256:c1eea424124103b058dcd837280b178650d7b1e8d6bf0e71d550071db0608923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UASROSX4GDLJXNCRKE5HEOBECF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Named Entity Recognition in Industrial Tables using Tabular Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aneta Koleva, Mark Buckley, Martin Ringsquandl, Rakebul Hasan, Volker Tresp","submitted_at":"2022-09-29T14:25:44Z","abstract_excerpt":"Specialized transformer-based models for encoding tabular data have gained interest in academia. Although tabular data is omnipresent in industry, applications of table transformers are still missing. In this paper, we study how these models can be applied to an industrial Named Entity Recognition (NER) problem where the entities are mentioned in tabular-structured spreadsheets. The highly technical nature of spreadsheets as well as the lack of labeled data present major challenges for fine-tuning transformer-based models. Therefore, we develop a dedicated table data augmentation strategy base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14812","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/2209.14812/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZF2MM9TcIrwHSkLDnql1IvtJ3TG3L+jFlh2kuc/pETK4az2FcWpmIYVblIWGC6VuknhHHPYy5dLdszg9YCbIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:18:13.878714Z"},"content_sha256":"91c28e19a51ca3e146815fd65f129dcfea6ff2c7943e21045b3fa5a2975ef7fc","schema_version":"1.0","event_id":"sha256:91c28e19a51ca3e146815fd65f129dcfea6ff2c7943e21045b3fa5a2975ef7fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UASROSX4GDLJXNCRKE5HEOBECF/bundle.json","state_url":"https://pith.science/pith/UASROSX4GDLJXNCRKE5HEOBECF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UASROSX4GDLJXNCRKE5HEOBECF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T20:18:13Z","links":{"resolver":"https://pith.science/pith/UASROSX4GDLJXNCRKE5HEOBECF","bundle":"https://pith.science/pith/UASROSX4GDLJXNCRKE5HEOBECF/bundle.json","state":"https://pith.science/pith/UASROSX4GDLJXNCRKE5HEOBECF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UASROSX4GDLJXNCRKE5HEOBECF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UASROSX4GDLJXNCRKE5HEOBECF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f02428da2686a151ec1fcf4fa0938848c7760b9735b681f89aca50a1e884a1c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-09-29T14:25:44Z","title_canon_sha256":"cd8811c5a3a35ab34f607b952815f369bdcdbeeac3595e9f3390dcbc8625e3a2"},"schema_version":"1.0","source":{"id":"2209.14812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14812","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14812v1","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14812","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"UASROSX4GDLJ","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"UASROSX4GDLJXNCR","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"UASROSX4","created_at":"2026-07-05T05:02:05Z"}],"graph_snapshots":[{"event_id":"sha256:91c28e19a51ca3e146815fd65f129dcfea6ff2c7943e21045b3fa5a2975ef7fc","target":"graph","created_at":"2026-07-05T05:02:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.14812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Specialized transformer-based models for encoding tabular data have gained interest in academia. Although tabular data is omnipresent in industry, applications of table transformers are still missing. In this paper, we study how these models can be applied to an industrial Named Entity Recognition (NER) problem where the entities are mentioned in tabular-structured spreadsheets. The highly technical nature of spreadsheets as well as the lack of labeled data present major challenges for fine-tuning transformer-based models. Therefore, we develop a dedicated table data augmentation strategy base","authors_text":"Aneta Koleva, Mark Buckley, Martin Ringsquandl, Rakebul Hasan, Volker Tresp","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-09-29T14:25:44Z","title":"Named Entity Recognition in Industrial Tables using Tabular Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14812","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c1eea424124103b058dcd837280b178650d7b1e8d6bf0e71d550071db0608923","target":"record","created_at":"2026-07-05T05:02:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f02428da2686a151ec1fcf4fa0938848c7760b9735b681f89aca50a1e884a1c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-09-29T14:25:44Z","title_canon_sha256":"cd8811c5a3a35ab34f607b952815f369bdcdbeeac3595e9f3390dcbc8625e3a2"},"schema_version":"1.0","source":{"id":"2209.14812","kind":"arxiv","version":1}},"canonical_sha256":"a025174afc30d69bb451513a7238241156cecd60839cdce6c8ea868974423d45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a025174afc30d69bb451513a7238241156cecd60839cdce6c8ea868974423d45","first_computed_at":"2026-07-05T05:02:05.979620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:05.979620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZpjvIvoKv7PvhlgN2CSHsUkOyLwJyddfGhE6AG8vrR6x7iUWCfzQ30fLo1VjWhtzE1xc914UCuBAhvbiBJisAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:05.980025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1eea424124103b058dcd837280b178650d7b1e8d6bf0e71d550071db0608923","sha256:91c28e19a51ca3e146815fd65f129dcfea6ff2c7943e21045b3fa5a2975ef7fc"],"state_sha256":"d70fe2b655023a9f401c4696e47241c2ea17372d76167bfd1450db35e8d97303"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xRX1FAP/aQNhQpJY5x9hkvNww3e4ug2dhA/At4dlklAECMaSiNxMqYWonfZU2yPSwxR3n7Hvl8zo/+lxjnqUAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:18:13.895628Z","bundle_sha256":"4dc940efe3709f07a9380d9cfbfa8f68d9c6b290a60e968d0ca8c79bf709d8bd"}}