{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:XTI6IOWUA3JP5L5J73QO2YKEP2","short_pith_number":"pith:XTI6IOWU","canonical_record":{"source":{"id":"1512.06034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-18T16:56:02Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"35a1fc12ee507d232de044a9d18d6450781716e743f0be9cd4c9c80f5dabc1c1","abstract_canon_sha256":"a099acda0c1e1575cbce093b670435e892e8114c9096d1af5a5cf3e2cced6aa3"},"schema_version":"1.0"},"canonical_sha256":"bcd1e43ad406d2feafa9fee0ed61447e96ebad1082097257ea436ea422324060","source":{"kind":"arxiv","id":"1512.06034","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.06034","created_at":"2026-05-18T01:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"1512.06034v1","created_at":"2026-05-18T01:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.06034","created_at":"2026-05-18T01:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"XTI6IOWUA3JP","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XTI6IOWUA3JP5L5J","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XTI6IOWU","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:XTI6IOWUA3JP5L5J73QO2YKEP2","target":"record","payload":{"canonical_record":{"source":{"id":"1512.06034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-18T16:56:02Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"35a1fc12ee507d232de044a9d18d6450781716e743f0be9cd4c9c80f5dabc1c1","abstract_canon_sha256":"a099acda0c1e1575cbce093b670435e892e8114c9096d1af5a5cf3e2cced6aa3"},"schema_version":"1.0"},"canonical_sha256":"bcd1e43ad406d2feafa9fee0ed61447e96ebad1082097257ea436ea422324060","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:05.578495Z","signature_b64":"j+sfZMbA9ORIFOOSB/zYeSvsfbylY2GpsTru1zwtQyAaicV4fBCxASbNUmuykFp/j8lH5H+hIOfboZlJXiO3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcd1e43ad406d2feafa9fee0ed61447e96ebad1082097257ea436ea422324060","last_reissued_at":"2026-05-18T01:24:05.577786Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:05.577786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.06034","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":"2026-05-18T01:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0u9YuKJ8Tu0OJh+OgttJ5gWsvZi7SR5tWlIdct2PM4kMyfCqnwBOYhRn7FEKcHO6ki4ub5pWxJT9Wg05v2JSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T04:34:47.675122Z"},"content_sha256":"d1e5355e5f35d84ee7c1be98ed5be104d9be1c126f9593366bb92511f0468102","schema_version":"1.0","event_id":"sha256:d1e5355e5f35d84ee7c1be98ed5be104d9be1c126f9593366bb92511f0468102"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:XTI6IOWUA3JP5L5J73QO2YKEP2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ontology-driven Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Marco Manna, Nicola Leone, Weronika T. Adrian","submitted_at":"2015-12-18T16:56:02Z","abstract_excerpt":"Homogeneous unstructured data (HUD) are collections of unstructured documents that share common properties, such as similar layout, common file format, or common domain of values. Building on such properties, it would be desirable to automatically process HUD to access the main information through a semantic layer -- typically an ontology -- called semantic view. Hence, we propose an ontology-based approach for extracting semantically rich information from HUD, by integrating and extending recent technologies and results from the fields of classical information extraction, table recognition, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.06034","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":"2026-05-18T01:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RjhECNwLsQaV6Szh2Ekxsmlk0V7j7+bkvRhcU3VCRYJhANE6JgTz01eF4c+CXGQ3J7Af4WHUfkKyM23408UlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T04:34:47.675499Z"},"content_sha256":"49912321ac3efbf397e13cfa5cc24efe389a765ce68d9d35822b2a18bb17550e","schema_version":"1.0","event_id":"sha256:49912321ac3efbf397e13cfa5cc24efe389a765ce68d9d35822b2a18bb17550e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTI6IOWUA3JP5L5J73QO2YKEP2/bundle.json","state_url":"https://pith.science/pith/XTI6IOWUA3JP5L5J73QO2YKEP2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTI6IOWUA3JP5L5J73QO2YKEP2/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":"2026-06-24T04:34:47Z","links":{"resolver":"https://pith.science/pith/XTI6IOWUA3JP5L5J73QO2YKEP2","bundle":"https://pith.science/pith/XTI6IOWUA3JP5L5J73QO2YKEP2/bundle.json","state":"https://pith.science/pith/XTI6IOWUA3JP5L5J73QO2YKEP2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTI6IOWUA3JP5L5J73QO2YKEP2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:XTI6IOWUA3JP5L5J73QO2YKEP2","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":"a099acda0c1e1575cbce093b670435e892e8114c9096d1af5a5cf3e2cced6aa3","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-18T16:56:02Z","title_canon_sha256":"35a1fc12ee507d232de044a9d18d6450781716e743f0be9cd4c9c80f5dabc1c1"},"schema_version":"1.0","source":{"id":"1512.06034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.06034","created_at":"2026-05-18T01:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"1512.06034v1","created_at":"2026-05-18T01:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.06034","created_at":"2026-05-18T01:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"XTI6IOWUA3JP","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XTI6IOWUA3JP5L5J","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XTI6IOWU","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:49912321ac3efbf397e13cfa5cc24efe389a765ce68d9d35822b2a18bb17550e","target":"graph","created_at":"2026-05-18T01:24:05Z","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"},"paper":{"abstract_excerpt":"Homogeneous unstructured data (HUD) are collections of unstructured documents that share common properties, such as similar layout, common file format, or common domain of values. Building on such properties, it would be desirable to automatically process HUD to access the main information through a semantic layer -- typically an ontology -- called semantic view. Hence, we propose an ontology-based approach for extracting semantically rich information from HUD, by integrating and extending recent technologies and results from the fields of classical information extraction, table recognition, o","authors_text":"Marco Manna, Nicola Leone, Weronika T. Adrian","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-18T16:56:02Z","title":"Ontology-driven Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.06034","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:d1e5355e5f35d84ee7c1be98ed5be104d9be1c126f9593366bb92511f0468102","target":"record","created_at":"2026-05-18T01:24:05Z","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":"a099acda0c1e1575cbce093b670435e892e8114c9096d1af5a5cf3e2cced6aa3","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-18T16:56:02Z","title_canon_sha256":"35a1fc12ee507d232de044a9d18d6450781716e743f0be9cd4c9c80f5dabc1c1"},"schema_version":"1.0","source":{"id":"1512.06034","kind":"arxiv","version":1}},"canonical_sha256":"bcd1e43ad406d2feafa9fee0ed61447e96ebad1082097257ea436ea422324060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcd1e43ad406d2feafa9fee0ed61447e96ebad1082097257ea436ea422324060","first_computed_at":"2026-05-18T01:24:05.577786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:24:05.577786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+sfZMbA9ORIFOOSB/zYeSvsfbylY2GpsTru1zwtQyAaicV4fBCxASbNUmuykFp/j8lH5H+hIOfboZlJXiO3Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:24:05.578495Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.06034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1e5355e5f35d84ee7c1be98ed5be104d9be1c126f9593366bb92511f0468102","sha256:49912321ac3efbf397e13cfa5cc24efe389a765ce68d9d35822b2a18bb17550e"],"state_sha256":"f5d023260466b04979e980d20d41d82fc14f0f5890513e8fd79a23b62c63f7a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IdBh/BUJ6C/53At0tmzzWOji1kOt/ripvNvhYXBBE7AQIRiGsgAlKuxADK/SQp1213u+gtVSAnyBJXVfbXt0AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T04:34:47.677449Z","bundle_sha256":"af07f77dd5626eec0035e1a4cbf949c47452ebe455fb37e7bc542dcdd1210fca"}}