{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OBAKWF6EJPNPWNX7BOZVZSSJ6Z","short_pith_number":"pith:OBAKWF6E","canonical_record":{"source":{"id":"1807.09842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-24T04:14:51Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"97310e6c3a0a405112841ca12cada85db50f8ddc7e3ea6829295612c690644aa","abstract_canon_sha256":"3172c6c0e180f0fed74105638b65afad57353224b6079e6e5daaf7645938ddfe"},"schema_version":"1.0"},"canonical_sha256":"7040ab17c44bdafb36ff0bb35cca49f67646f4235271c2b673d3021196542aae","source":{"kind":"arxiv","id":"1807.09842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09842","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09842v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09842","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"OBAKWF6EJPNP","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OBAKWF6EJPNPWNX7","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OBAKWF6E","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OBAKWF6EJPNPWNX7BOZVZSSJ6Z","target":"record","payload":{"canonical_record":{"source":{"id":"1807.09842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-24T04:14:51Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"97310e6c3a0a405112841ca12cada85db50f8ddc7e3ea6829295612c690644aa","abstract_canon_sha256":"3172c6c0e180f0fed74105638b65afad57353224b6079e6e5daaf7645938ddfe"},"schema_version":"1.0"},"canonical_sha256":"7040ab17c44bdafb36ff0bb35cca49f67646f4235271c2b673d3021196542aae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:46.432450Z","signature_b64":"frtLOoMFVokwXMG3ZHHg8+0vjzmpIajC8rXLSdMEmo2+6ZpNSIDh9mY2qSnNfbW3BjvQEE45fUrEgmu3yKfRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7040ab17c44bdafb36ff0bb35cca49f67646f4235271c2b673d3021196542aae","last_reissued_at":"2026-05-18T00:09:46.431640Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:46.431640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.09842","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":"2026-05-18T00:09:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXvjKpUH0KRM3NtljtAHYe4lMJxv6mgB0LXuV3ewqjnuhY8kSM/2mAg7jFq2AB/mkMFDecOGAqytnwpHbI1dBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:06:28.090092Z"},"content_sha256":"2835e0ca1ee1f6e5176480e6849621ed9bf50ad925782af33dad949f35d1d53e","schema_version":"1.0","event_id":"sha256:2835e0ca1ee1f6e5176480e6849621ed9bf50ad925782af33dad949f35d1d53e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OBAKWF6EJPNPWNX7BOZVZSSJ6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding and representing the semantics of large structured documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Muhammad Mahbubur Rahman, Tim Finin","submitted_at":"2018-07-24T04:14:51Z","abstract_excerpt":"Understanding large, structured documents like scholarly articles, requests for proposals or business reports is a complex and difficult task. It involves discovering a document's overall purpose and subject(s), understanding the function and meaning of its sections and subsections, and extracting low level entities and facts about them. In this research, we present a deep learning based document ontology to capture the general purpose semantic structure and domain specific semantic concepts from a large number of academic articles and business documents. The ontology is able to describe diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09842","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":"2026-05-18T00:09:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AS3H3fIF+dFTCMh/b8FeAPOvlz7IgEn8pY7iRABfFbFakSXNLfYSdc7oWFqoo04GsQ58oDA2k6jCKNqVhArqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:06:28.090444Z"},"content_sha256":"e7b5dfa91ce0b5373fdce2cfa4e92b4f779f4c364ed20717a65c3008390f05b3","schema_version":"1.0","event_id":"sha256:e7b5dfa91ce0b5373fdce2cfa4e92b4f779f4c364ed20717a65c3008390f05b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OBAKWF6EJPNPWNX7BOZVZSSJ6Z/bundle.json","state_url":"https://pith.science/pith/OBAKWF6EJPNPWNX7BOZVZSSJ6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OBAKWF6EJPNPWNX7BOZVZSSJ6Z/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":"2026-06-02T23:06:28Z","links":{"resolver":"https://pith.science/pith/OBAKWF6EJPNPWNX7BOZVZSSJ6Z","bundle":"https://pith.science/pith/OBAKWF6EJPNPWNX7BOZVZSSJ6Z/bundle.json","state":"https://pith.science/pith/OBAKWF6EJPNPWNX7BOZVZSSJ6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OBAKWF6EJPNPWNX7BOZVZSSJ6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OBAKWF6EJPNPWNX7BOZVZSSJ6Z","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":"3172c6c0e180f0fed74105638b65afad57353224b6079e6e5daaf7645938ddfe","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-24T04:14:51Z","title_canon_sha256":"97310e6c3a0a405112841ca12cada85db50f8ddc7e3ea6829295612c690644aa"},"schema_version":"1.0","source":{"id":"1807.09842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09842","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09842v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09842","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"OBAKWF6EJPNP","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OBAKWF6EJPNPWNX7","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OBAKWF6E","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:e7b5dfa91ce0b5373fdce2cfa4e92b4f779f4c364ed20717a65c3008390f05b3","target":"graph","created_at":"2026-05-18T00:09:46Z","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":"Understanding large, structured documents like scholarly articles, requests for proposals or business reports is a complex and difficult task. It involves discovering a document's overall purpose and subject(s), understanding the function and meaning of its sections and subsections, and extracting low level entities and facts about them. In this research, we present a deep learning based document ontology to capture the general purpose semantic structure and domain specific semantic concepts from a large number of academic articles and business documents. The ontology is able to describe diffe","authors_text":"Muhammad Mahbubur Rahman, Tim Finin","cross_cats":["cs.IR","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-24T04:14:51Z","title":"Understanding and representing the semantics of large structured documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09842","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":"sha256:2835e0ca1ee1f6e5176480e6849621ed9bf50ad925782af33dad949f35d1d53e","target":"record","created_at":"2026-05-18T00:09:46Z","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":"3172c6c0e180f0fed74105638b65afad57353224b6079e6e5daaf7645938ddfe","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-24T04:14:51Z","title_canon_sha256":"97310e6c3a0a405112841ca12cada85db50f8ddc7e3ea6829295612c690644aa"},"schema_version":"1.0","source":{"id":"1807.09842","kind":"arxiv","version":1}},"canonical_sha256":"7040ab17c44bdafb36ff0bb35cca49f67646f4235271c2b673d3021196542aae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7040ab17c44bdafb36ff0bb35cca49f67646f4235271c2b673d3021196542aae","first_computed_at":"2026-05-18T00:09:46.431640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:46.431640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"frtLOoMFVokwXMG3ZHHg8+0vjzmpIajC8rXLSdMEmo2+6ZpNSIDh9mY2qSnNfbW3BjvQEE45fUrEgmu3yKfRAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:46.432450Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.09842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2835e0ca1ee1f6e5176480e6849621ed9bf50ad925782af33dad949f35d1d53e","sha256:e7b5dfa91ce0b5373fdce2cfa4e92b4f779f4c364ed20717a65c3008390f05b3"],"state_sha256":"93563ad201a9482fa0c38ee65f1b5964d6d9d6b9c933a99035231e8563bd48ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mJ7KdW33AqZzKWnvLxUdytWjdsNvnbMdY/9ybQo8y7uZsRr0c/3NoidIcCMBELswm0mOyWXmrcA8y+dQbqlJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:06:28.092264Z","bundle_sha256":"df7692eff4bb903184c8292edb2a87b2d82e214489d0c6989c2d0ce8c109cfa4"}}