{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:I3PM2BDYBMAGXSN427BVO2MNGU","short_pith_number":"pith:I3PM2BDY","canonical_record":{"source":{"id":"1902.10526","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T13:48:59Z","cross_cats_sorted":[],"title_canon_sha256":"b0dc72422016a0f79b158efc05c1ab031cbd74a4b9fb91f72911fa2123bb448c","abstract_canon_sha256":"42d0c7e3507aa211b24aebffa537c586123f2d84c35303b010515ae1c09d1348"},"schema_version":"1.0"},"canonical_sha256":"46decd04780b006bc9bcd7c357698d352bdb687156f988e443638f428eb16b35","source":{"kind":"arxiv","id":"1902.10526","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10526","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10526v3","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10526","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"I3PM2BDYBMAG","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"I3PM2BDYBMAGXSN4","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"I3PM2BDY","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:I3PM2BDYBMAGXSN427BVO2MNGU","target":"record","payload":{"canonical_record":{"source":{"id":"1902.10526","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T13:48:59Z","cross_cats_sorted":[],"title_canon_sha256":"b0dc72422016a0f79b158efc05c1ab031cbd74a4b9fb91f72911fa2123bb448c","abstract_canon_sha256":"42d0c7e3507aa211b24aebffa537c586123f2d84c35303b010515ae1c09d1348"},"schema_version":"1.0"},"canonical_sha256":"46decd04780b006bc9bcd7c357698d352bdb687156f988e443638f428eb16b35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:04.923094Z","signature_b64":"VBu8h9QV8R+/q5UpOeIW3R/tRvwiqYoj9xT+Bh7cAGqpQIqyLYL1hb1xjCxK96St0+UUDXCdKzvhDse2EOKzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46decd04780b006bc9bcd7c357698d352bdb687156f988e443638f428eb16b35","last_reissued_at":"2026-05-17T23:51:04.922402Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:04.922402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.10526","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mHQjj9DGudQSLiUIcz73mZIwHaBJef+Cpn1vquGjY/55wb6Cw1wzeEAoSjL6BjFMNITdgGEm5crcVPknOFhNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:54:14.353716Z"},"content_sha256":"c7e0d03c8dec58bfbd39877be19f9eb7ceff3718db98d0ec9ec137f2234b220f","schema_version":"1.0","event_id":"sha256:c7e0d03c8dec58bfbd39877be19f9eb7ceff3718db98d0ec9ec137f2234b220f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:I3PM2BDYBMAGXSN427BVO2MNGU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Malmi, Idan Szpektor, Jonathan Berant, Mor Geva","submitted_at":"2019-02-27T13:48:59Z","abstract_excerpt":"Sentence fusion is the task of joining several independent sentences into a single coherent text. Current datasets for sentence fusion are small and insufficient for training modern neural models. In this paper, we propose a method for automatically-generating fusion examples from raw text and present DiscoFuse, a large scale dataset for discourse-based sentence fusion. We author a set of rules for identifying a diverse set of discourse phenomena in raw text, and decomposing the text into two independent sentences. We apply our approach on two document collections: Wikipedia and Sports article"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10526","kind":"arxiv","version":3},"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":"2026-05-17T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cruJYYPNXWuyZZQvc1YzAUnQBGo7wLFRuMrrQrXpeifZ5Qa+eVloq7U5afCr08f1NiJRZ18lskTrO61kFBSYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:54:14.354347Z"},"content_sha256":"c30b66c6ed9570313a59018b5baa1a1f503be78c1dac7c6f2ddf403a625b1fc7","schema_version":"1.0","event_id":"sha256:c30b66c6ed9570313a59018b5baa1a1f503be78c1dac7c6f2ddf403a625b1fc7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3PM2BDYBMAGXSN427BVO2MNGU/bundle.json","state_url":"https://pith.science/pith/I3PM2BDYBMAGXSN427BVO2MNGU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3PM2BDYBMAGXSN427BVO2MNGU/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":"2026-05-26T06:54:14Z","links":{"resolver":"https://pith.science/pith/I3PM2BDYBMAGXSN427BVO2MNGU","bundle":"https://pith.science/pith/I3PM2BDYBMAGXSN427BVO2MNGU/bundle.json","state":"https://pith.science/pith/I3PM2BDYBMAGXSN427BVO2MNGU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3PM2BDYBMAGXSN427BVO2MNGU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:I3PM2BDYBMAGXSN427BVO2MNGU","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":"42d0c7e3507aa211b24aebffa537c586123f2d84c35303b010515ae1c09d1348","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T13:48:59Z","title_canon_sha256":"b0dc72422016a0f79b158efc05c1ab031cbd74a4b9fb91f72911fa2123bb448c"},"schema_version":"1.0","source":{"id":"1902.10526","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10526","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10526v3","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10526","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"I3PM2BDYBMAG","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"I3PM2BDYBMAGXSN4","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"I3PM2BDY","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:c30b66c6ed9570313a59018b5baa1a1f503be78c1dac7c6f2ddf403a625b1fc7","target":"graph","created_at":"2026-05-17T23:51:04Z","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":"Sentence fusion is the task of joining several independent sentences into a single coherent text. Current datasets for sentence fusion are small and insufficient for training modern neural models. In this paper, we propose a method for automatically-generating fusion examples from raw text and present DiscoFuse, a large scale dataset for discourse-based sentence fusion. We author a set of rules for identifying a diverse set of discourse phenomena in raw text, and decomposing the text into two independent sentences. We apply our approach on two document collections: Wikipedia and Sports article","authors_text":"Eric Malmi, Idan Szpektor, Jonathan Berant, Mor Geva","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T13:48:59Z","title":"DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10526","kind":"arxiv","version":3},"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:c7e0d03c8dec58bfbd39877be19f9eb7ceff3718db98d0ec9ec137f2234b220f","target":"record","created_at":"2026-05-17T23:51:04Z","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":"42d0c7e3507aa211b24aebffa537c586123f2d84c35303b010515ae1c09d1348","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T13:48:59Z","title_canon_sha256":"b0dc72422016a0f79b158efc05c1ab031cbd74a4b9fb91f72911fa2123bb448c"},"schema_version":"1.0","source":{"id":"1902.10526","kind":"arxiv","version":3}},"canonical_sha256":"46decd04780b006bc9bcd7c357698d352bdb687156f988e443638f428eb16b35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46decd04780b006bc9bcd7c357698d352bdb687156f988e443638f428eb16b35","first_computed_at":"2026-05-17T23:51:04.922402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:04.922402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VBu8h9QV8R+/q5UpOeIW3R/tRvwiqYoj9xT+Bh7cAGqpQIqyLYL1hb1xjCxK96St0+UUDXCdKzvhDse2EOKzCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:04.923094Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10526","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7e0d03c8dec58bfbd39877be19f9eb7ceff3718db98d0ec9ec137f2234b220f","sha256:c30b66c6ed9570313a59018b5baa1a1f503be78c1dac7c6f2ddf403a625b1fc7"],"state_sha256":"c1faebe5a025e8fb71647f1ed3f84fc236b4172a4c7dbb6792db37f6c56865f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9SVO+sVC768XL850xkuHHJbtyuj6l35RyGZ4jLyaBeTioaheuR1Vvs3Du8tt3CZt+tMSW3ZPgohORvRT+zhjAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:54:14.358105Z","bundle_sha256":"0378888840c4dbd7cd7ec8288955ddd159eeab59eef03c03784f7f92e86160a0"}}