{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EC526ON52L4D4GHSXSCP2JK3OD","short_pith_number":"pith:EC526ON5","canonical_record":{"source":{"id":"1811.05546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T22:08:39Z","cross_cats_sorted":[],"title_canon_sha256":"4e2068be1c870f3ecd2b7c2392a46cd57196cdbb8ca290b336b1973056350151","abstract_canon_sha256":"f62651a1c6c5da9fa5fa9c6028f6b10694a91822844501bc0a5a8d73b637f649"},"schema_version":"1.0"},"canonical_sha256":"20bbaf39bdd2f83e18f2bc84fd255b70f31802d5425e95beebe270def422eca1","source":{"kind":"arxiv","id":"1811.05546","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05546","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05546v1","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05546","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"EC526ON52L4D","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EC526ON52L4D4GHS","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EC526ON5","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EC526ON52L4D4GHSXSCP2JK3OD","target":"record","payload":{"canonical_record":{"source":{"id":"1811.05546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T22:08:39Z","cross_cats_sorted":[],"title_canon_sha256":"4e2068be1c870f3ecd2b7c2392a46cd57196cdbb8ca290b336b1973056350151","abstract_canon_sha256":"f62651a1c6c5da9fa5fa9c6028f6b10694a91822844501bc0a5a8d73b637f649"},"schema_version":"1.0"},"canonical_sha256":"20bbaf39bdd2f83e18f2bc84fd255b70f31802d5425e95beebe270def422eca1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:42.675146Z","signature_b64":"C0tzhJP4pZeE4AABvPsX6yJdr7Fx3Q4/WETL3aaRu8tL5Bq37FFROxfBJ+3lgpCsCBpLP8HRALBk8sVj1UguBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20bbaf39bdd2f83e18f2bc84fd255b70f31802d5425e95beebe270def422eca1","last_reissued_at":"2026-05-18T00:00:42.674762Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:42.674762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.05546","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":"2026-05-18T00:00:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HYiUXPpRi0H9gxLhaKSFKam1m6wcwoOSKlNVOaUPy1U4xs1o8iyjkz9hLU5boX5NuBv1KH1HyxuSU5NF34kzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:16:25.028482Z"},"content_sha256":"4efc357f357c49d55edb30aa07c0b6b4356a272a8ffdbb2025f5a9de7292ee48","schema_version":"1.0","event_id":"sha256:4efc357f357c49d55edb30aa07c0b6b4356a272a8ffdbb2025f5a9de7292ee48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EC526ON52L4D4GHSXSCP2JK3OD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discourse in Multimedia: A Case Study in Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Eduard H. Hovy, Eric P. Xing, Kumar Avinava Dubey, Mrinmaya Sachan, Tom M. Mitchell","submitted_at":"2018-11-13T22:08:39Z","abstract_excerpt":"To ensure readability, text is often written and presented with due formatting. These text formatting devices help the writer to effectively convey the narrative. At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information. There have been a number of linguistic theories on discourse structure of text. However, these theories only consider unformatted text. Multimedia text contains rich formatting features which can be leveraged for various NLP tasks. In this paper, we study some of these discourse features in multimedia text and what"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05546","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":"2026-05-18T00:00:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZHn7tgZVVzK5mPIAG9MNvoByTsY2Xk7Nz4hZrUNXXtaDpmDCS2GsvoZbQOlwz/Ei/sLhI44rsm7uiXMxr1UmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:16:25.028829Z"},"content_sha256":"828d363535998be0adb349c74631e5c41880b407bffb75169b163954f69920e5","schema_version":"1.0","event_id":"sha256:828d363535998be0adb349c74631e5c41880b407bffb75169b163954f69920e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EC526ON52L4D4GHSXSCP2JK3OD/bundle.json","state_url":"https://pith.science/pith/EC526ON52L4D4GHSXSCP2JK3OD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EC526ON52L4D4GHSXSCP2JK3OD/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":"2026-05-30T13:16:25Z","links":{"resolver":"https://pith.science/pith/EC526ON52L4D4GHSXSCP2JK3OD","bundle":"https://pith.science/pith/EC526ON52L4D4GHSXSCP2JK3OD/bundle.json","state":"https://pith.science/pith/EC526ON52L4D4GHSXSCP2JK3OD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EC526ON52L4D4GHSXSCP2JK3OD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EC526ON52L4D4GHSXSCP2JK3OD","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":"f62651a1c6c5da9fa5fa9c6028f6b10694a91822844501bc0a5a8d73b637f649","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T22:08:39Z","title_canon_sha256":"4e2068be1c870f3ecd2b7c2392a46cd57196cdbb8ca290b336b1973056350151"},"schema_version":"1.0","source":{"id":"1811.05546","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05546","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05546v1","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05546","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"EC526ON52L4D","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EC526ON52L4D4GHS","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EC526ON5","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:828d363535998be0adb349c74631e5c41880b407bffb75169b163954f69920e5","target":"graph","created_at":"2026-05-18T00:00:42Z","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":"To ensure readability, text is often written and presented with due formatting. These text formatting devices help the writer to effectively convey the narrative. At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information. There have been a number of linguistic theories on discourse structure of text. However, these theories only consider unformatted text. Multimedia text contains rich formatting features which can be leveraged for various NLP tasks. In this paper, we study some of these discourse features in multimedia text and what","authors_text":"Dan Roth, Eduard H. Hovy, Eric P. Xing, Kumar Avinava Dubey, Mrinmaya Sachan, Tom M. Mitchell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T22:08:39Z","title":"Discourse in Multimedia: A Case Study in Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05546","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":"sha256:4efc357f357c49d55edb30aa07c0b6b4356a272a8ffdbb2025f5a9de7292ee48","target":"record","created_at":"2026-05-18T00:00:42Z","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":"f62651a1c6c5da9fa5fa9c6028f6b10694a91822844501bc0a5a8d73b637f649","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T22:08:39Z","title_canon_sha256":"4e2068be1c870f3ecd2b7c2392a46cd57196cdbb8ca290b336b1973056350151"},"schema_version":"1.0","source":{"id":"1811.05546","kind":"arxiv","version":1}},"canonical_sha256":"20bbaf39bdd2f83e18f2bc84fd255b70f31802d5425e95beebe270def422eca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20bbaf39bdd2f83e18f2bc84fd255b70f31802d5425e95beebe270def422eca1","first_computed_at":"2026-05-18T00:00:42.674762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:42.674762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C0tzhJP4pZeE4AABvPsX6yJdr7Fx3Q4/WETL3aaRu8tL5Bq37FFROxfBJ+3lgpCsCBpLP8HRALBk8sVj1UguBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:42.675146Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.05546","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4efc357f357c49d55edb30aa07c0b6b4356a272a8ffdbb2025f5a9de7292ee48","sha256:828d363535998be0adb349c74631e5c41880b407bffb75169b163954f69920e5"],"state_sha256":"6ce50fdf4ef10e7772d76b0624d81f1e51082a4b1cdcfe8b53430711391250ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUP3hzZIoJleYk0laK9WGnu39d9jCLRRxWifXBitDiTbYJ7TE/EjwD8cjIiRf0O2ay1K5oie0j8cvmTfVb97CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:16:25.031123Z","bundle_sha256":"dec8d563a16b21d8ddd866850015b285008e67b16cfb75ce0a662b570079686d"}}