{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WM6EUJFVQCO5RF37OAVCD5HMB3","short_pith_number":"pith:WM6EUJFV","canonical_record":{"source":{"id":"2104.01785","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2021-04-05T06:05:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"96938efaf2babb08dfc8d328b5992c7440d320953d0ebd982cd7b05a43611967","abstract_canon_sha256":"7287395801498d5be8c4c3ae4f7a489e843ba6312731821796411ab9874a985f"},"schema_version":"1.0"},"canonical_sha256":"b33c4a24b5809dd8977f702a21f4ec0ef539b25f366299dbf3cbf85f8fe5c75a","source":{"kind":"arxiv","id":"2104.01785","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01785","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01785v2","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01785","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"WM6EUJFVQCO5","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"WM6EUJFVQCO5RF37","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"WM6EUJFV","created_at":"2026-07-05T04:00:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WM6EUJFVQCO5RF37OAVCD5HMB3","target":"record","payload":{"canonical_record":{"source":{"id":"2104.01785","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2021-04-05T06:05:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"96938efaf2babb08dfc8d328b5992c7440d320953d0ebd982cd7b05a43611967","abstract_canon_sha256":"7287395801498d5be8c4c3ae4f7a489e843ba6312731821796411ab9874a985f"},"schema_version":"1.0"},"canonical_sha256":"b33c4a24b5809dd8977f702a21f4ec0ef539b25f366299dbf3cbf85f8fe5c75a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:51.984080Z","signature_b64":"yg+sQVeuwjkMK1bx1QZVa+CMN1INkfGrjBtsSItS7piCsWmnIBaW/LY6ytAmCyE4sWuqDNfHsJ2lGdkyOEaSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b33c4a24b5809dd8977f702a21f4ec0ef539b25f366299dbf3cbf85f8fe5c75a","last_reissued_at":"2026-07-05T04:00:51.983576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:51.983576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.01785","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:00:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1pAh4Ad3nb97F0Dy14HY9QvMhcbtpAyzhRh5Qf8qeLJioxLkwnHclOeBo8/R8SCuX5fcanyVPvl2lrB2vjJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T17:22:07.104728Z"},"content_sha256":"b0663ac7873617fdd0448a17cbde2a90855643f2bd5e795170febd1809b904b8","schema_version":"1.0","event_id":"sha256:b0663ac7873617fdd0448a17cbde2a90855643f2bd5e795170febd1809b904b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WM6EUJFVQCO5RF37OAVCD5HMB3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Annotating Columns with Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"\\c{C}a\\u{g}atay Demiralp, Chen Chen, Dan Zhang, Jinfeng Li, Wang-Chiew Tan, Yoshihiko Suhara, Yuliang Li","submitted_at":"2021-04-05T06:05:01Z","abstract_excerpt":"Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information. In this paper, we study the problem of annotating table columns (i.e., predicting column types and the relationships between columns) using only information from the table itself. We develop a multi-task learning framework (called Doduo) based on pre-trained language models, which takes the entire table as input and predicts column types/relations using a single model. Experimental results s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01785","kind":"arxiv","version":2},"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/2104.01785/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":"2026-07-05T04:00:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8/qmKxZ/FVQ/QumBnH29v6QeXQ1fD1KnhSuJ29kKmH7EL5mvOyciLFE/b4L5N+hIptZjcfWrRk/0gjlRQ3IDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T17:22:07.105584Z"},"content_sha256":"2de0a49d0f1a120adbc01d4dfd0f57fdb39fccb03622d9c4abbca104edbdf474","schema_version":"1.0","event_id":"sha256:2de0a49d0f1a120adbc01d4dfd0f57fdb39fccb03622d9c4abbca104edbdf474"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WM6EUJFVQCO5RF37OAVCD5HMB3/bundle.json","state_url":"https://pith.science/pith/WM6EUJFVQCO5RF37OAVCD5HMB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WM6EUJFVQCO5RF37OAVCD5HMB3/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":"2026-07-10T17:22:07Z","links":{"resolver":"https://pith.science/pith/WM6EUJFVQCO5RF37OAVCD5HMB3","bundle":"https://pith.science/pith/WM6EUJFVQCO5RF37OAVCD5HMB3/bundle.json","state":"https://pith.science/pith/WM6EUJFVQCO5RF37OAVCD5HMB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WM6EUJFVQCO5RF37OAVCD5HMB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WM6EUJFVQCO5RF37OAVCD5HMB3","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":"7287395801498d5be8c4c3ae4f7a489e843ba6312731821796411ab9874a985f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2021-04-05T06:05:01Z","title_canon_sha256":"96938efaf2babb08dfc8d328b5992c7440d320953d0ebd982cd7b05a43611967"},"schema_version":"1.0","source":{"id":"2104.01785","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01785","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01785v2","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01785","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"WM6EUJFVQCO5","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"WM6EUJFVQCO5RF37","created_at":"2026-07-05T04:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"WM6EUJFV","created_at":"2026-07-05T04:00:51Z"}],"graph_snapshots":[{"event_id":"sha256:2de0a49d0f1a120adbc01d4dfd0f57fdb39fccb03622d9c4abbca104edbdf474","target":"graph","created_at":"2026-07-05T04:00:51Z","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/2104.01785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information. In this paper, we study the problem of annotating table columns (i.e., predicting column types and the relationships between columns) using only information from the table itself. We develop a multi-task learning framework (called Doduo) based on pre-trained language models, which takes the entire table as input and predicts column types/relations using a single model. Experimental results s","authors_text":"\\c{C}a\\u{g}atay Demiralp, Chen Chen, Dan Zhang, Jinfeng Li, Wang-Chiew Tan, Yoshihiko Suhara, Yuliang Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2021-04-05T06:05:01Z","title":"Annotating Columns with Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01785","kind":"arxiv","version":2},"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:b0663ac7873617fdd0448a17cbde2a90855643f2bd5e795170febd1809b904b8","target":"record","created_at":"2026-07-05T04:00:51Z","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":"7287395801498d5be8c4c3ae4f7a489e843ba6312731821796411ab9874a985f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2021-04-05T06:05:01Z","title_canon_sha256":"96938efaf2babb08dfc8d328b5992c7440d320953d0ebd982cd7b05a43611967"},"schema_version":"1.0","source":{"id":"2104.01785","kind":"arxiv","version":2}},"canonical_sha256":"b33c4a24b5809dd8977f702a21f4ec0ef539b25f366299dbf3cbf85f8fe5c75a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b33c4a24b5809dd8977f702a21f4ec0ef539b25f366299dbf3cbf85f8fe5c75a","first_computed_at":"2026-07-05T04:00:51.983576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:00:51.983576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yg+sQVeuwjkMK1bx1QZVa+CMN1INkfGrjBtsSItS7piCsWmnIBaW/LY6ytAmCyE4sWuqDNfHsJ2lGdkyOEaSBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:00:51.984080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.01785","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0663ac7873617fdd0448a17cbde2a90855643f2bd5e795170febd1809b904b8","sha256:2de0a49d0f1a120adbc01d4dfd0f57fdb39fccb03622d9c4abbca104edbdf474"],"state_sha256":"7c22c6448b214e4717c4fafe9f25f839af81d151607371bc73e0e91f610a212a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8c2WpM7tfRW2SsG6tJkxvZXxA6qZX9AjxOPhZYIKAi0yKn8ovBXSAU8WCOMYw2zAzBtVaYVQBRijjQwZ9ChRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T17:22:07.110547Z","bundle_sha256":"6c6d0caae97e2766a5671dc7ac171a3eefb9ffe155cbc34f90995a76b898ec0c"}}