{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EBDMG7C2FKJKE3HQMFVIJG4QR2","short_pith_number":"pith:EBDMG7C2","canonical_record":{"source":{"id":"2209.00946","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-09-02T11:01:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3971362655440db57452b6077757af577ff9d704274196a872fbf1055620c391","abstract_canon_sha256":"a3921ec06bc930c584a0f9cb5cc6178e9f44fc5acfdf666cb6ee7fc16b0b59e1"},"schema_version":"1.0"},"canonical_sha256":"2046c37c5a2a92a26cf0616a849b908e898c42e54349f15c44914992f095ebea","source":{"kind":"arxiv","id":"2209.00946","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.00946","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"arxiv_version","alias_value":"2209.00946v2","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00946","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_12","alias_value":"EBDMG7C2FKJK","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_16","alias_value":"EBDMG7C2FKJKE3HQ","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_8","alias_value":"EBDMG7C2","created_at":"2026-07-05T06:14:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EBDMG7C2FKJKE3HQMFVIJG4QR2","target":"record","payload":{"canonical_record":{"source":{"id":"2209.00946","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-09-02T11:01:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3971362655440db57452b6077757af577ff9d704274196a872fbf1055620c391","abstract_canon_sha256":"a3921ec06bc930c584a0f9cb5cc6178e9f44fc5acfdf666cb6ee7fc16b0b59e1"},"schema_version":"1.0"},"canonical_sha256":"2046c37c5a2a92a26cf0616a849b908e898c42e54349f15c44914992f095ebea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:36.440393Z","signature_b64":"6V6uQ6d0uxUfOxxRYNH1Qcvifcmu0lDXk3TtyOslNY84DhCFrCVxvx0fSLkCD+g07KP18UTUR9s2RNrN82GeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2046c37c5a2a92a26cf0616a849b908e898c42e54349f15c44914992f095ebea","last_reissued_at":"2026-07-05T06:14:36.439893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:36.439893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.00946","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":"2026-07-05T06:14:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g9gCQ6GmqF5AcZJXz7IaHpy/0VLLqq19ENYHtLstTzjQDwy2Na82uBDa3qDpHhBt46OpZZynNxD0aqqG8mOFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:50:47.707635Z"},"content_sha256":"fca6904a53983656f682e7e48c43575a1e81eacecdd59628815f272ea6e1833a","schema_version":"1.0","event_id":"sha256:fca6904a53983656f682e7e48c43575a1e81eacecdd59628815f272ea6e1833a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EBDMG7C2FKJKE3HQMFVIJG4QR2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Dongmei Zhang, Jialiang Xu, Mengyu Zhou, Mingjie Zhou, Shi Han, Tianle Li, Xiao Lv, Xinyi He, Yijia Shao, Zejian Yuan","submitted_at":"2022-09-02T11:01:45Z","abstract_excerpt":"Tabular data analysis is performed every day across various domains. It requires an accurate understanding of field semantics to correctly operate on table fields and find common patterns in daily analysis. In this paper, we introduce the AnaMeta dataset, a collection of 467k tables with derived supervision labels for four types of commonly used field metadata: measure/dimension dichotomy, common field roles, semantic field type, and default aggregation function. We evaluate a wide range of models for inferring metadata as the benchmark. We also propose a multi-encoder framework, called KDF, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00946","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/2209.00946/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":"2026-07-05T06:14:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I/EzUzHSyBa/shMLlBICwL/Bq3QtBTcfLaScF8ZbMDgQZkSWqBDlzckK/Z4w1Nt9B3Dvb49pmPk3s8/tr/i5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:50:47.708121Z"},"content_sha256":"5311e1c62b8a7eb563ee51e9e42ad5ada0e82d03bd862787834a092bbf373fb3","schema_version":"1.0","event_id":"sha256:5311e1c62b8a7eb563ee51e9e42ad5ada0e82d03bd862787834a092bbf373fb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBDMG7C2FKJKE3HQMFVIJG4QR2/bundle.json","state_url":"https://pith.science/pith/EBDMG7C2FKJKE3HQMFVIJG4QR2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBDMG7C2FKJKE3HQMFVIJG4QR2/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":"2026-08-10T23:50:47Z","links":{"resolver":"https://pith.science/pith/EBDMG7C2FKJKE3HQMFVIJG4QR2","bundle":"https://pith.science/pith/EBDMG7C2FKJKE3HQMFVIJG4QR2/bundle.json","state":"https://pith.science/pith/EBDMG7C2FKJKE3HQMFVIJG4QR2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBDMG7C2FKJKE3HQMFVIJG4QR2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EBDMG7C2FKJKE3HQMFVIJG4QR2","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":"a3921ec06bc930c584a0f9cb5cc6178e9f44fc5acfdf666cb6ee7fc16b0b59e1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-09-02T11:01:45Z","title_canon_sha256":"3971362655440db57452b6077757af577ff9d704274196a872fbf1055620c391"},"schema_version":"1.0","source":{"id":"2209.00946","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.00946","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"arxiv_version","alias_value":"2209.00946v2","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00946","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_12","alias_value":"EBDMG7C2FKJK","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_16","alias_value":"EBDMG7C2FKJKE3HQ","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_8","alias_value":"EBDMG7C2","created_at":"2026-07-05T06:14:36Z"}],"graph_snapshots":[{"event_id":"sha256:5311e1c62b8a7eb563ee51e9e42ad5ada0e82d03bd862787834a092bbf373fb3","target":"graph","created_at":"2026-07-05T06:14:36Z","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/2209.00946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data analysis is performed every day across various domains. It requires an accurate understanding of field semantics to correctly operate on table fields and find common patterns in daily analysis. In this paper, we introduce the AnaMeta dataset, a collection of 467k tables with derived supervision labels for four types of commonly used field metadata: measure/dimension dichotomy, common field roles, semantic field type, and default aggregation function. We evaluate a wide range of models for inferring metadata as the benchmark. We also propose a multi-encoder framework, called KDF, w","authors_text":"Dongmei Zhang, Jialiang Xu, Mengyu Zhou, Mingjie Zhou, Shi Han, Tianle Li, Xiao Lv, Xinyi He, Yijia Shao, Zejian Yuan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-09-02T11:01:45Z","title":"AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00946","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:fca6904a53983656f682e7e48c43575a1e81eacecdd59628815f272ea6e1833a","target":"record","created_at":"2026-07-05T06:14:36Z","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":"a3921ec06bc930c584a0f9cb5cc6178e9f44fc5acfdf666cb6ee7fc16b0b59e1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2022-09-02T11:01:45Z","title_canon_sha256":"3971362655440db57452b6077757af577ff9d704274196a872fbf1055620c391"},"schema_version":"1.0","source":{"id":"2209.00946","kind":"arxiv","version":2}},"canonical_sha256":"2046c37c5a2a92a26cf0616a849b908e898c42e54349f15c44914992f095ebea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2046c37c5a2a92a26cf0616a849b908e898c42e54349f15c44914992f095ebea","first_computed_at":"2026-07-05T06:14:36.439893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:36.439893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6V6uQ6d0uxUfOxxRYNH1Qcvifcmu0lDXk3TtyOslNY84DhCFrCVxvx0fSLkCD+g07KP18UTUR9s2RNrN82GeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:36.440393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.00946","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fca6904a53983656f682e7e48c43575a1e81eacecdd59628815f272ea6e1833a","sha256:5311e1c62b8a7eb563ee51e9e42ad5ada0e82d03bd862787834a092bbf373fb3"],"state_sha256":"ec779beccb0b0ee3b98c858ae9fafa7bf2113cdfa4b57dc4317d666a98f468e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m47yAB54RZFShfw2t6v3EJ7MQ8W2eSw3BIkXPvBbbTAft40ARC5tH/mImKn+PXSr/Ucs1ONasmV/EB5POx2BBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:50:47.713349Z","bundle_sha256":"f933d5ce16acd0f2fbcf4f7a77fa5973ec65ddb5c2aaf8d0e810bfb9eab63e40"}}