{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YOO2UG5G27YUS7FBZOQPUKLI5D","short_pith_number":"pith:YOO2UG5G","canonical_record":{"source":{"id":"1901.08456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-24T15:31:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"710166958e8042a29fb88a2d6407a6b140d21e4cc22b939b767316dbdbcd6bcc","abstract_canon_sha256":"613901065914dc91cdd2a7a5cb4604a070ee18459543c9eba6a5693bce974843"},"schema_version":"1.0"},"canonical_sha256":"c39daa1ba6d7f1497ca1cba0fa2968e8d26afddc1011e9a9bca6e1ac0e055181","source":{"kind":"arxiv","id":"1901.08456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08456","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08456v1","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08456","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"pith_short_12","alias_value":"YOO2UG5G27YU","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YOO2UG5G27YUS7FB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YOO2UG5G","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YOO2UG5G27YUS7FBZOQPUKLI5D","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-24T15:31:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"710166958e8042a29fb88a2d6407a6b140d21e4cc22b939b767316dbdbcd6bcc","abstract_canon_sha256":"613901065914dc91cdd2a7a5cb4604a070ee18459543c9eba6a5693bce974843"},"schema_version":"1.0"},"canonical_sha256":"c39daa1ba6d7f1497ca1cba0fa2968e8d26afddc1011e9a9bca6e1ac0e055181","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:35.388418Z","signature_b64":"awws9fGQczOfJzJeZGX2iXgE1a2yRTr9KO+QPVpKXJ7bjbPU3NjreFFC2iQJrKdIE+XQnLPzsxtfhgllFr2sBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c39daa1ba6d7f1497ca1cba0fa2968e8d26afddc1011e9a9bca6e1ac0e055181","last_reissued_at":"2026-05-17T23:55:35.387803Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:35.387803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08456","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":"2026-05-17T23:55:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BrJx6OezDF7RyXt8kIDMipRh3yrVsBuhP89TgDBfd6R5NVZ5HIpDfPh/kf5a6M6BGDPE1pvMfUw9WoqeD5mHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:55:50.719781Z"},"content_sha256":"8f52c2c42caf6fbf97c8e1447aeec1084d55a1e631c88620e6dd5e9ed6d8398d","schema_version":"1.0","event_id":"sha256:8f52c2c42caf6fbf97c8e1447aeec1084d55a1e631c88620e6dd5e9ed6d8398d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YOO2UG5G27YUS7FBZOQPUKLI5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Classification of Tabular Datasets via Character-Level Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Craig Corcoran, David Sullivan, Garrett Honke, Jeffrey Gleason, Jonathon Morgan, Numa Dhamani, Paul Azunre, Rebecca Ruppel, Sandeep Verma","submitted_at":"2019-01-24T15:31:11Z","abstract_excerpt":"A character-level convolutional neural network (CNN) motivated by applications in \"automated machine learning\" (AutoML) is proposed to semantically classify columns in tabular data. Simulated data containing a set of base classes is first used to learn an initial set of weights. Hand-labeled data from the CKAN repository is then used in a transfer-learning paradigm to adapt the initial weights to a more sophisticated representation of the problem (e.g., including more classes). In doing so, realistic data imperfections are learned and the set of classes handled can be expanded from the base se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08456","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":""},"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":"2026-05-17T23:55:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UhbbHdaOvhbZlFJ+XNoxFeyl0uJ7t+/rEayvXbIdrEPchFhNOCxiXdjmW2QceaXCpPAOqKqLm4pSgaLjS2qYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:55:50.720325Z"},"content_sha256":"6fcadf7790cbbda5abaa3f6638afd3bf5eaf2c6bfe62d053969789f7d5803f98","schema_version":"1.0","event_id":"sha256:6fcadf7790cbbda5abaa3f6638afd3bf5eaf2c6bfe62d053969789f7d5803f98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOO2UG5G27YUS7FBZOQPUKLI5D/bundle.json","state_url":"https://pith.science/pith/YOO2UG5G27YUS7FBZOQPUKLI5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOO2UG5G27YUS7FBZOQPUKLI5D/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":"2026-06-05T04:55:50Z","links":{"resolver":"https://pith.science/pith/YOO2UG5G27YUS7FBZOQPUKLI5D","bundle":"https://pith.science/pith/YOO2UG5G27YUS7FBZOQPUKLI5D/bundle.json","state":"https://pith.science/pith/YOO2UG5G27YUS7FBZOQPUKLI5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOO2UG5G27YUS7FBZOQPUKLI5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YOO2UG5G27YUS7FBZOQPUKLI5D","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":"613901065914dc91cdd2a7a5cb4604a070ee18459543c9eba6a5693bce974843","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-24T15:31:11Z","title_canon_sha256":"710166958e8042a29fb88a2d6407a6b140d21e4cc22b939b767316dbdbcd6bcc"},"schema_version":"1.0","source":{"id":"1901.08456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08456","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08456v1","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08456","created_at":"2026-05-17T23:55:35Z"},{"alias_kind":"pith_short_12","alias_value":"YOO2UG5G27YU","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YOO2UG5G27YUS7FB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YOO2UG5G","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:6fcadf7790cbbda5abaa3f6638afd3bf5eaf2c6bfe62d053969789f7d5803f98","target":"graph","created_at":"2026-05-17T23:55:35Z","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"},"paper":{"abstract_excerpt":"A character-level convolutional neural network (CNN) motivated by applications in \"automated machine learning\" (AutoML) is proposed to semantically classify columns in tabular data. Simulated data containing a set of base classes is first used to learn an initial set of weights. Hand-labeled data from the CKAN repository is then used in a transfer-learning paradigm to adapt the initial weights to a more sophisticated representation of the problem (e.g., including more classes). In doing so, realistic data imperfections are learned and the set of classes handled can be expanded from the base se","authors_text":"Craig Corcoran, David Sullivan, Garrett Honke, Jeffrey Gleason, Jonathon Morgan, Numa Dhamani, Paul Azunre, Rebecca Ruppel, Sandeep Verma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-24T15:31:11Z","title":"Semantic Classification of Tabular Datasets via Character-Level Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08456","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":"sha256:8f52c2c42caf6fbf97c8e1447aeec1084d55a1e631c88620e6dd5e9ed6d8398d","target":"record","created_at":"2026-05-17T23:55:35Z","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":"613901065914dc91cdd2a7a5cb4604a070ee18459543c9eba6a5693bce974843","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-24T15:31:11Z","title_canon_sha256":"710166958e8042a29fb88a2d6407a6b140d21e4cc22b939b767316dbdbcd6bcc"},"schema_version":"1.0","source":{"id":"1901.08456","kind":"arxiv","version":1}},"canonical_sha256":"c39daa1ba6d7f1497ca1cba0fa2968e8d26afddc1011e9a9bca6e1ac0e055181","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c39daa1ba6d7f1497ca1cba0fa2968e8d26afddc1011e9a9bca6e1ac0e055181","first_computed_at":"2026-05-17T23:55:35.387803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:35.387803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"awws9fGQczOfJzJeZGX2iXgE1a2yRTr9KO+QPVpKXJ7bjbPU3NjreFFC2iQJrKdIE+XQnLPzsxtfhgllFr2sBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:35.388418Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f52c2c42caf6fbf97c8e1447aeec1084d55a1e631c88620e6dd5e9ed6d8398d","sha256:6fcadf7790cbbda5abaa3f6638afd3bf5eaf2c6bfe62d053969789f7d5803f98"],"state_sha256":"f82154b255a849f31405c69b51f26295664f917b13bea6a64545dc3613f20f3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PLRrtf4dTkBPHr+YXvBRGFkH25r6jU+Cjcmdf296R2vOKHIjfwGlwpDDUcuhxXTVEjvTWSJnayBIe47VkkcEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T04:55:50.723066Z","bundle_sha256":"faa4124070945fd414f53bbac3e3add6e818f0cdbc6f9cc9e3fdddfc42c2f8bd"}}