{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Y7TSOLCIR3LA7P5RNAYPSD3WYF","short_pith_number":"pith:Y7TSOLCI","canonical_record":{"source":{"id":"1709.00770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T21:38:56Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"1c50d924d9f8af9ad5a2eb17a3883809ad64b11bf38506476809b5c2e0155e32","abstract_canon_sha256":"a96c79fff4eb762d5c8f5ce427a38b93d563b684ce5a0a203c8e125fc2b243ff"},"schema_version":"1.0"},"canonical_sha256":"c7e7272c488ed60fbfb16830f90f76c16a40e1120b30aa3bb3036c16c4b79c40","source":{"kind":"arxiv","id":"1709.00770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00770","created_at":"2026-05-18T00:36:05Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00770v1","created_at":"2026-05-18T00:36:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00770","created_at":"2026-05-18T00:36:05Z"},{"alias_kind":"pith_short_12","alias_value":"Y7TSOLCIR3LA","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y7TSOLCIR3LA7P5R","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y7TSOLCI","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Y7TSOLCIR3LA7P5RNAYPSD3WYF","target":"record","payload":{"canonical_record":{"source":{"id":"1709.00770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T21:38:56Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"1c50d924d9f8af9ad5a2eb17a3883809ad64b11bf38506476809b5c2e0155e32","abstract_canon_sha256":"a96c79fff4eb762d5c8f5ce427a38b93d563b684ce5a0a203c8e125fc2b243ff"},"schema_version":"1.0"},"canonical_sha256":"c7e7272c488ed60fbfb16830f90f76c16a40e1120b30aa3bb3036c16c4b79c40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:05.206746Z","signature_b64":"5M8hcRKfUCIkKA30ZZy0Fu/O4ufWzd4L78uR0Cymx12dobg+qlSN5PyPhF584bJPZHYPo228DdIoFpZ1ZnfmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7e7272c488ed60fbfb16830f90f76c16a40e1120b30aa3bb3036c16c4b79c40","last_reissued_at":"2026-05-18T00:36:05.206072Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:05.206072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.00770","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":"2026-05-18T00:36:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cX21pOmNEz3LSAGshnwVt+zOLe6QcYvNvxr5JokbfQEsDMhvhdJT7KwcEDx+BvvYA9bWOI19UPvzeI0++B3GCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:47:04.233869Z"},"content_sha256":"19312ce61bc97825e880bff77e43f1c87b206745c90dc35aa19afba1c0d5e54e","schema_version":"1.0","event_id":"sha256:19312ce61bc97825e880bff77e43f1c87b206745c90dc35aa19afba1c0d5e54e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Y7TSOLCIR3LA7P5RNAYPSD3WYF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the Logical and Semantic Structure of Large Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Muhammad Mahbubur Rahman, Tim Finin","submitted_at":"2017-09-03T21:38:56Z","abstract_excerpt":"Current language understanding approaches focus on small documents, such as newswire articles, blog posts, product reviews and discussion forum entries. Understanding and extracting information from large documents like legal briefs, proposals, technical manuals and research articles is still a challenging task. We describe a framework that can analyze a large document and help people to know where a particular information is in that document. We aim to automatically identify and classify semantic sections of documents and assign consistent and human-understandable labels to similar sections a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00770","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":"2026-05-18T00:36:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FNDUoxYhy+HLrFf237zO2YNPUr2leI2hixdg8ej52IUCjPoSBDPmhkhPbRvIOB+PonKsIkDiupT+oQZDDSOJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:47:04.234240Z"},"content_sha256":"32f5beabf3c5e7e1aa454dea8ec00be6174ce0c694862c6c9d3dc9c4340ef38c","schema_version":"1.0","event_id":"sha256:32f5beabf3c5e7e1aa454dea8ec00be6174ce0c694862c6c9d3dc9c4340ef38c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7TSOLCIR3LA7P5RNAYPSD3WYF/bundle.json","state_url":"https://pith.science/pith/Y7TSOLCIR3LA7P5RNAYPSD3WYF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7TSOLCIR3LA7P5RNAYPSD3WYF/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":"2026-06-02T20:47:04Z","links":{"resolver":"https://pith.science/pith/Y7TSOLCIR3LA7P5RNAYPSD3WYF","bundle":"https://pith.science/pith/Y7TSOLCIR3LA7P5RNAYPSD3WYF/bundle.json","state":"https://pith.science/pith/Y7TSOLCIR3LA7P5RNAYPSD3WYF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7TSOLCIR3LA7P5RNAYPSD3WYF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Y7TSOLCIR3LA7P5RNAYPSD3WYF","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":"a96c79fff4eb762d5c8f5ce427a38b93d563b684ce5a0a203c8e125fc2b243ff","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T21:38:56Z","title_canon_sha256":"1c50d924d9f8af9ad5a2eb17a3883809ad64b11bf38506476809b5c2e0155e32"},"schema_version":"1.0","source":{"id":"1709.00770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00770","created_at":"2026-05-18T00:36:05Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00770v1","created_at":"2026-05-18T00:36:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00770","created_at":"2026-05-18T00:36:05Z"},{"alias_kind":"pith_short_12","alias_value":"Y7TSOLCIR3LA","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y7TSOLCIR3LA7P5R","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y7TSOLCI","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:32f5beabf3c5e7e1aa454dea8ec00be6174ce0c694862c6c9d3dc9c4340ef38c","target":"graph","created_at":"2026-05-18T00:36:05Z","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":"Current language understanding approaches focus on small documents, such as newswire articles, blog posts, product reviews and discussion forum entries. Understanding and extracting information from large documents like legal briefs, proposals, technical manuals and research articles is still a challenging task. We describe a framework that can analyze a large document and help people to know where a particular information is in that document. We aim to automatically identify and classify semantic sections of documents and assign consistent and human-understandable labels to similar sections a","authors_text":"Muhammad Mahbubur Rahman, Tim Finin","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T21:38:56Z","title":"Understanding the Logical and Semantic Structure of Large Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00770","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":"sha256:19312ce61bc97825e880bff77e43f1c87b206745c90dc35aa19afba1c0d5e54e","target":"record","created_at":"2026-05-18T00:36:05Z","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":"a96c79fff4eb762d5c8f5ce427a38b93d563b684ce5a0a203c8e125fc2b243ff","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-03T21:38:56Z","title_canon_sha256":"1c50d924d9f8af9ad5a2eb17a3883809ad64b11bf38506476809b5c2e0155e32"},"schema_version":"1.0","source":{"id":"1709.00770","kind":"arxiv","version":1}},"canonical_sha256":"c7e7272c488ed60fbfb16830f90f76c16a40e1120b30aa3bb3036c16c4b79c40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7e7272c488ed60fbfb16830f90f76c16a40e1120b30aa3bb3036c16c4b79c40","first_computed_at":"2026-05-18T00:36:05.206072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:05.206072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5M8hcRKfUCIkKA30ZZy0Fu/O4ufWzd4L78uR0Cymx12dobg+qlSN5PyPhF584bJPZHYPo228DdIoFpZ1ZnfmDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:05.206746Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19312ce61bc97825e880bff77e43f1c87b206745c90dc35aa19afba1c0d5e54e","sha256:32f5beabf3c5e7e1aa454dea8ec00be6174ce0c694862c6c9d3dc9c4340ef38c"],"state_sha256":"b1dbe3dc218884db7c3b6c2d13957ed71ad9c67195268381829e4b8db97d6519"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJIeOEmOxX1UEADMFE2NeZCiflrcAZyXlLD7nZhj0OTak1ZrM+0l4kkAn7hp6/pc4q4R8IGaXqpPUlHUFlTNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:47:04.236348Z","bundle_sha256":"6153b784e1d7271958fc6d30049b059d2ebc6c4ad62c57e3d3ec08d92023a0ed"}}