{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:54EU3YGXVRBDOBIFLJBG2W2MJ7","short_pith_number":"pith:54EU3YGX","canonical_record":{"source":{"id":"1703.05028","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-15T09:12:29Z","cross_cats_sorted":[],"title_canon_sha256":"fa2bbeb59f988b5a7abbd9d50a74ae7807d91bf4291aec75bded189020df8b8c","abstract_canon_sha256":"729f2587e716eeafd036783d6b9c63be685be1e46c735892e51ea1fdad36ea17"},"schema_version":"1.0"},"canonical_sha256":"ef094de0d7ac423705055a426d5b4c4fff433c4b20d115679a141b89d672eb19","source":{"kind":"arxiv","id":"1703.05028","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05028","created_at":"2026-05-18T00:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05028v2","created_at":"2026-05-18T00:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05028","created_at":"2026-05-18T00:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"54EU3YGXVRBD","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"54EU3YGXVRBDOBIF","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"54EU3YGX","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:54EU3YGXVRBDOBIFLJBG2W2MJ7","target":"record","payload":{"canonical_record":{"source":{"id":"1703.05028","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-15T09:12:29Z","cross_cats_sorted":[],"title_canon_sha256":"fa2bbeb59f988b5a7abbd9d50a74ae7807d91bf4291aec75bded189020df8b8c","abstract_canon_sha256":"729f2587e716eeafd036783d6b9c63be685be1e46c735892e51ea1fdad36ea17"},"schema_version":"1.0"},"canonical_sha256":"ef094de0d7ac423705055a426d5b4c4fff433c4b20d115679a141b89d672eb19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:11.084985Z","signature_b64":"WFX/Jj5fSKeKBWMHYsYZ/CV1nisq2Zz8HN838pSW/p6h724KxmiuGifn14Fgk3rF3oMA08EAh7H9dsGq9rFQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef094de0d7ac423705055a426d5b4c4fff433c4b20d115679a141b89d672eb19","last_reissued_at":"2026-05-18T00:22:11.084555Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:11.084555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.05028","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":"2026-05-18T00:22:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"89Vd6zB1KZ1ltI+Sx4FeaujzEcZJJ3T5guHgLcIp+8Wyd6hA4Alo57YhFxNY4sL+xr5NwiuIyOSc/3M8wxltBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:22:34.422511Z"},"content_sha256":"099dd59bdf5b5b8c1923aa080cf9b3d7347b9042285b3ed188295775a7a1cf65","schema_version":"1.0","event_id":"sha256:099dd59bdf5b5b8c1923aa080cf9b3d7347b9042285b3ed188295775a7a1cf65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:54EU3YGXVRBDOBIFLJBG2W2MJ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fonduer: Knowledge Base Construction from Richly Formatted Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Braden Hancock, Christopher R\\'e, Luke Hsiao, Philip Levis, Sen Wu, Theodoros Rekatsinas, Xiao Cheng","submitted_at":"2017-03-15T09:12:29Z","abstract_excerpt":"We focus on knowledge base construction (KBC) from richly formatted data. In contrast to KBC from text or tabular data, KBC from richly formatted data aims to extract relations conveyed jointly via textual, structural, tabular, and visual expressions. We introduce Fonduer, a machine-learning-based KBC system for richly formatted data. Fonduer presents a new data model that accounts for three challenging characteristics of richly formatted data: (1) prevalent document-level relations, (2) multimodality, and (3) data variety. Fonduer uses a new deep-learning model to automatically capture the re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05028","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":""},"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":"2026-05-18T00:22:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50U6cQ/kLE+zxqfqJHklR+WdTPJ54+iT0EpsOwN8CwFC6FV5Oee61v4FLV3ZWNBG0FHONDPaycvF1e5CgeCYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:22:34.423247Z"},"content_sha256":"3dff4c5c3f69bfeda030dfd9e55f5305c8c8126bff7aba3ae93f23710599d4b6","schema_version":"1.0","event_id":"sha256:3dff4c5c3f69bfeda030dfd9e55f5305c8c8126bff7aba3ae93f23710599d4b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54EU3YGXVRBDOBIFLJBG2W2MJ7/bundle.json","state_url":"https://pith.science/pith/54EU3YGXVRBDOBIFLJBG2W2MJ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54EU3YGXVRBDOBIFLJBG2W2MJ7/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":"2026-06-12T02:22:34Z","links":{"resolver":"https://pith.science/pith/54EU3YGXVRBDOBIFLJBG2W2MJ7","bundle":"https://pith.science/pith/54EU3YGXVRBDOBIFLJBG2W2MJ7/bundle.json","state":"https://pith.science/pith/54EU3YGXVRBDOBIFLJBG2W2MJ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54EU3YGXVRBDOBIFLJBG2W2MJ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:54EU3YGXVRBDOBIFLJBG2W2MJ7","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":"729f2587e716eeafd036783d6b9c63be685be1e46c735892e51ea1fdad36ea17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-15T09:12:29Z","title_canon_sha256":"fa2bbeb59f988b5a7abbd9d50a74ae7807d91bf4291aec75bded189020df8b8c"},"schema_version":"1.0","source":{"id":"1703.05028","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05028","created_at":"2026-05-18T00:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05028v2","created_at":"2026-05-18T00:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05028","created_at":"2026-05-18T00:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"54EU3YGXVRBD","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"54EU3YGXVRBDOBIF","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"54EU3YGX","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:3dff4c5c3f69bfeda030dfd9e55f5305c8c8126bff7aba3ae93f23710599d4b6","target":"graph","created_at":"2026-05-18T00:22:11Z","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":"We focus on knowledge base construction (KBC) from richly formatted data. In contrast to KBC from text or tabular data, KBC from richly formatted data aims to extract relations conveyed jointly via textual, structural, tabular, and visual expressions. We introduce Fonduer, a machine-learning-based KBC system for richly formatted data. Fonduer presents a new data model that accounts for three challenging characteristics of richly formatted data: (1) prevalent document-level relations, (2) multimodality, and (3) data variety. Fonduer uses a new deep-learning model to automatically capture the re","authors_text":"Braden Hancock, Christopher R\\'e, Luke Hsiao, Philip Levis, Sen Wu, Theodoros Rekatsinas, Xiao Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-15T09:12:29Z","title":"Fonduer: Knowledge Base Construction from Richly Formatted Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05028","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":"sha256:099dd59bdf5b5b8c1923aa080cf9b3d7347b9042285b3ed188295775a7a1cf65","target":"record","created_at":"2026-05-18T00:22:11Z","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":"729f2587e716eeafd036783d6b9c63be685be1e46c735892e51ea1fdad36ea17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-15T09:12:29Z","title_canon_sha256":"fa2bbeb59f988b5a7abbd9d50a74ae7807d91bf4291aec75bded189020df8b8c"},"schema_version":"1.0","source":{"id":"1703.05028","kind":"arxiv","version":2}},"canonical_sha256":"ef094de0d7ac423705055a426d5b4c4fff433c4b20d115679a141b89d672eb19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef094de0d7ac423705055a426d5b4c4fff433c4b20d115679a141b89d672eb19","first_computed_at":"2026-05-18T00:22:11.084555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:11.084555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WFX/Jj5fSKeKBWMHYsYZ/CV1nisq2Zz8HN838pSW/p6h724KxmiuGifn14Fgk3rF3oMA08EAh7H9dsGq9rFQDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:11.084985Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.05028","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:099dd59bdf5b5b8c1923aa080cf9b3d7347b9042285b3ed188295775a7a1cf65","sha256:3dff4c5c3f69bfeda030dfd9e55f5305c8c8126bff7aba3ae93f23710599d4b6"],"state_sha256":"1ec7bf05ddb83ae1753dcb16fab0cb05dbb40c45a74fa6d5baeb5892be27e30d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O36RvcAsGne8+99uMRvi3MiuySZYXS1n07o4iVQyQm49K+JRPHOp92WgmH7SS8qEayRTL8DFxuZ+i2vL8ZmaBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T02:22:34.427462Z","bundle_sha256":"1e5ff3f3bd42c328469d9288d3120b2656cea5b5b05c3ef008f7ae45fc019cfa"}}