{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7FWIEZS7UHV7KOJ5NJBD33FAYN","short_pith_number":"pith:7FWIEZS7","canonical_record":{"source":{"id":"2004.14535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T01:36:52Z","cross_cats_sorted":[],"title_canon_sha256":"b474eb7a3dbcb8e55df26de87408f1493850845ffd23367ee810040e4be71588","abstract_canon_sha256":"d87f6dd95c24bf2a47bd6b75d40ad7a2b99d9deb9308f24c41f3feb23900c462"},"schema_version":"1.0"},"canonical_sha256":"f96c82665fa1ebf5393d6a423deca0c371a6ddd2a988e89dc0b0990469ad6e34","source":{"kind":"arxiv","id":"2004.14535","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14535","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14535v2","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14535","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"pith_short_12","alias_value":"7FWIEZS7UHV7","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"pith_short_16","alias_value":"7FWIEZS7UHV7KOJ5","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"pith_short_8","alias_value":"7FWIEZS7","created_at":"2026-07-05T01:57:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7FWIEZS7UHV7KOJ5NJBD33FAYN","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T01:36:52Z","cross_cats_sorted":[],"title_canon_sha256":"b474eb7a3dbcb8e55df26de87408f1493850845ffd23367ee810040e4be71588","abstract_canon_sha256":"d87f6dd95c24bf2a47bd6b75d40ad7a2b99d9deb9308f24c41f3feb23900c462"},"schema_version":"1.0"},"canonical_sha256":"f96c82665fa1ebf5393d6a423deca0c371a6ddd2a988e89dc0b0990469ad6e34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:16.490321Z","signature_b64":"nETM+7JunLSOtSTnodhImFy609tm7HEkOUVNyj9A+n6wa+0dfFSytUlmoWgz/oU8HplvWaLi0DhkEKuK/XMRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f96c82665fa1ebf5393d6a423deca0c371a6ddd2a988e89dc0b0990469ad6e34","last_reissued_at":"2026-07-05T01:57:16.489848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:16.489848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14535","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":"2026-07-05T01:57:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUjc8R2UOJboXX8sX2jOskQKDioNaShI9r3nqZB49Foazy/mN5AHwgsNn1bxueCBNtQXaYvaokDlc+zX6ifwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:16:31.178838Z"},"content_sha256":"2980206d5158d28fc096f6fe22a1bc67d4b327ba84ac664cb2a2e6df90820ed4","schema_version":"1.0","event_id":"sha256:2980206d5158d28fc096f6fe22a1bc67d4b327ba84ac664cb2a2e6df90820ed4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7FWIEZS7UHV7KOJ5NJBD33FAYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Segmentation by Cross Segment Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boris Dadachev, Gon\\c{c}alo Sim\\~oes, Kishore Papineni, Michal Lukasik","submitted_at":"2020-04-30T01:36:52Z","abstract_excerpt":"Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents, which are commonly used to help downstream tasks such as information retrieval or text summarization. In this work, we propose three transformer-based architectures and provide comprehensive comparisons with previously proposed approaches on three standard datasets. We establish a new state-of-the-art, reducing in particular the error rates by a large margin in all cases. We further analyze model sizes and find that we can build models with many fewer parameters while keeping goo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14535","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.14535/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:57:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mIngZSheZ7QQpEAkkNVB7CVxkm/0Ay4PtDJT/io2PrGVcB60lLh6E8hAp5ztKbH89KiqTyNWFY4mbg/Y1nq+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:16:31.179588Z"},"content_sha256":"c16fdaf0bbea48878c36604eddbdf64ab64545dbddb36cd6d84a9846e0e1bf19","schema_version":"1.0","event_id":"sha256:c16fdaf0bbea48878c36604eddbdf64ab64545dbddb36cd6d84a9846e0e1bf19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7FWIEZS7UHV7KOJ5NJBD33FAYN/bundle.json","state_url":"https://pith.science/pith/7FWIEZS7UHV7KOJ5NJBD33FAYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7FWIEZS7UHV7KOJ5NJBD33FAYN/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":"2026-08-10T12:16:31Z","links":{"resolver":"https://pith.science/pith/7FWIEZS7UHV7KOJ5NJBD33FAYN","bundle":"https://pith.science/pith/7FWIEZS7UHV7KOJ5NJBD33FAYN/bundle.json","state":"https://pith.science/pith/7FWIEZS7UHV7KOJ5NJBD33FAYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7FWIEZS7UHV7KOJ5NJBD33FAYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7FWIEZS7UHV7KOJ5NJBD33FAYN","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":"d87f6dd95c24bf2a47bd6b75d40ad7a2b99d9deb9308f24c41f3feb23900c462","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T01:36:52Z","title_canon_sha256":"b474eb7a3dbcb8e55df26de87408f1493850845ffd23367ee810040e4be71588"},"schema_version":"1.0","source":{"id":"2004.14535","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14535","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14535v2","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14535","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"pith_short_12","alias_value":"7FWIEZS7UHV7","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"pith_short_16","alias_value":"7FWIEZS7UHV7KOJ5","created_at":"2026-07-05T01:57:16Z"},{"alias_kind":"pith_short_8","alias_value":"7FWIEZS7","created_at":"2026-07-05T01:57:16Z"}],"graph_snapshots":[{"event_id":"sha256:c16fdaf0bbea48878c36604eddbdf64ab64545dbddb36cd6d84a9846e0e1bf19","target":"graph","created_at":"2026-07-05T01:57:16Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.14535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents, which are commonly used to help downstream tasks such as information retrieval or text summarization. In this work, we propose three transformer-based architectures and provide comprehensive comparisons with previously proposed approaches on three standard datasets. We establish a new state-of-the-art, reducing in particular the error rates by a large margin in all cases. We further analyze model sizes and find that we can build models with many fewer parameters while keeping goo","authors_text":"Boris Dadachev, Gon\\c{c}alo Sim\\~oes, Kishore Papineni, Michal Lukasik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T01:36:52Z","title":"Text Segmentation by Cross Segment Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14535","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":"sha256:2980206d5158d28fc096f6fe22a1bc67d4b327ba84ac664cb2a2e6df90820ed4","target":"record","created_at":"2026-07-05T01:57:16Z","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":"d87f6dd95c24bf2a47bd6b75d40ad7a2b99d9deb9308f24c41f3feb23900c462","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T01:36:52Z","title_canon_sha256":"b474eb7a3dbcb8e55df26de87408f1493850845ffd23367ee810040e4be71588"},"schema_version":"1.0","source":{"id":"2004.14535","kind":"arxiv","version":2}},"canonical_sha256":"f96c82665fa1ebf5393d6a423deca0c371a6ddd2a988e89dc0b0990469ad6e34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f96c82665fa1ebf5393d6a423deca0c371a6ddd2a988e89dc0b0990469ad6e34","first_computed_at":"2026-07-05T01:57:16.489848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:16.489848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nETM+7JunLSOtSTnodhImFy609tm7HEkOUVNyj9A+n6wa+0dfFSytUlmoWgz/oU8HplvWaLi0DhkEKuK/XMRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:16.490321Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14535","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2980206d5158d28fc096f6fe22a1bc67d4b327ba84ac664cb2a2e6df90820ed4","sha256:c16fdaf0bbea48878c36604eddbdf64ab64545dbddb36cd6d84a9846e0e1bf19"],"state_sha256":"2e62ee952786a70fc008aaa6d9af41f2f06206bd8047efcc373130a322292f86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRzs/4c7ROZUbHR058Mh+vSJ0clqi0MPcqbNUmNG4xQZsj2cF5POS9GulqWZdgZz7zPqJXBipgcnOcaanohPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:16:31.188796Z","bundle_sha256":"f9d80e56ecbb2bd443b1603b9efce5e162ec877bcff2c673710b3eaed6b0fa0d"}}