{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7MI7NGIMYMXO62WEQIWD2KQQRU","short_pith_number":"pith:7MI7NGIM","canonical_record":{"source":{"id":"2501.07723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:18:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddf8d2048bc841f67233e690d7a4028464224eecd8008bdca5715f85c23c12c7","abstract_canon_sha256":"51e2e9bf3ecaabc5d5a05c6439238520564c9de6c99a62cec10bc249f994d4b7"},"schema_version":"1.0"},"canonical_sha256":"fb11f6990cc32eef6ac4822c3d2a108d0d9457e30e4dc0c497bda64ce693e0e8","source":{"kind":"arxiv","id":"2501.07723","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07723","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07723v1","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07723","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"7MI7NGIMYMXO","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"7MI7NGIMYMXO62WE","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"7MI7NGIM","created_at":"2026-07-05T10:00:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7MI7NGIMYMXO62WEQIWD2KQQRU","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:18:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddf8d2048bc841f67233e690d7a4028464224eecd8008bdca5715f85c23c12c7","abstract_canon_sha256":"51e2e9bf3ecaabc5d5a05c6439238520564c9de6c99a62cec10bc249f994d4b7"},"schema_version":"1.0"},"canonical_sha256":"fb11f6990cc32eef6ac4822c3d2a108d0d9457e30e4dc0c497bda64ce693e0e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:49.109911Z","signature_b64":"4z1N7VMYV/ha+xFCRkTRsGEbjVj0uJuE0g2hiH1p4EK9MZGT/g4AgF31lTwD3MAAxHmSsR/UMiKRNAv6unvcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb11f6990cc32eef6ac4822c3d2a108d0d9457e30e4dc0c497bda64ce693e0e8","last_reissued_at":"2026-07-05T10:00:49.109522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:49.109522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07723","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":"2026-07-05T10:00:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6maTRSNmiV4YYpU6NrO9EW+NGaD6fODd9VHotrQHIzXjj3EDwtUpbWSSyTUi91Tb8Kl7d8zuTeSbZ0aVufADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:14:00.683213Z"},"content_sha256":"735e97bbf05e91ec4d9874d46941b525c6e409dbf4a7f3a8e3776ecee6bab7d2","schema_version":"1.0","event_id":"sha256:735e97bbf05e91ec4d9874d46941b525c6e409dbf4a7f3a8e3776ecee6bab7d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7MI7NGIMYMXO62WEQIWD2KQQRU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ESURF: Simple and Effective EDU Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Mohammadreza Sediqin, Shlomo Engelson Argamon","submitted_at":"2025-01-13T22:18:52Z","abstract_excerpt":"Segmenting text into Elemental Discourse Units (EDUs) is a fundamental task in discourse parsing. We present a new simple method for identifying EDU boundaries, and hence segmenting them, based on lexical and character n-gram features, using random forest classification. We show that the method, despite its simplicity, outperforms other methods both for segmentation and within a state of the art discourse parser. This indicates the importance of such features for identifying basic discourse elements, pointing towards potentially more training-efficient methods for discourse analysis."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07723","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.07723/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":"2026-07-05T10:00:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0AQ6Dpw4pUTRCjSMDVK1LdKRNwevM2vPRSxJyWslqLXgMN9h7L8tD4xcgYW2+nHDjyCnFVpRTBTOAf8uuiMOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:14:00.684415Z"},"content_sha256":"7c5cb88a8a5b6a711f17469cb5132e2464674fbfa9a417e64b8c48db0eeafd85","schema_version":"1.0","event_id":"sha256:7c5cb88a8a5b6a711f17469cb5132e2464674fbfa9a417e64b8c48db0eeafd85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/bundle.json","state_url":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/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":"2026-08-18T18:14:00Z","links":{"resolver":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU","bundle":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/bundle.json","state":"https://pith.science/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MI7NGIMYMXO62WEQIWD2KQQRU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7MI7NGIMYMXO62WEQIWD2KQQRU","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":"51e2e9bf3ecaabc5d5a05c6439238520564c9de6c99a62cec10bc249f994d4b7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:18:52Z","title_canon_sha256":"ddf8d2048bc841f67233e690d7a4028464224eecd8008bdca5715f85c23c12c7"},"schema_version":"1.0","source":{"id":"2501.07723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07723","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07723v1","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07723","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"7MI7NGIMYMXO","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"7MI7NGIMYMXO62WE","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"7MI7NGIM","created_at":"2026-07-05T10:00:49Z"}],"graph_snapshots":[{"event_id":"sha256:7c5cb88a8a5b6a711f17469cb5132e2464674fbfa9a417e64b8c48db0eeafd85","target":"graph","created_at":"2026-07-05T10:00:49Z","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/2501.07723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Segmenting text into Elemental Discourse Units (EDUs) is a fundamental task in discourse parsing. We present a new simple method for identifying EDU boundaries, and hence segmenting them, based on lexical and character n-gram features, using random forest classification. We show that the method, despite its simplicity, outperforms other methods both for segmentation and within a state of the art discourse parser. This indicates the importance of such features for identifying basic discourse elements, pointing towards potentially more training-efficient methods for discourse analysis.","authors_text":"Mohammadreza Sediqin, Shlomo Engelson Argamon","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:18:52Z","title":"ESURF: Simple and Effective EDU Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07723","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":"sha256:735e97bbf05e91ec4d9874d46941b525c6e409dbf4a7f3a8e3776ecee6bab7d2","target":"record","created_at":"2026-07-05T10:00:49Z","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":"51e2e9bf3ecaabc5d5a05c6439238520564c9de6c99a62cec10bc249f994d4b7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:18:52Z","title_canon_sha256":"ddf8d2048bc841f67233e690d7a4028464224eecd8008bdca5715f85c23c12c7"},"schema_version":"1.0","source":{"id":"2501.07723","kind":"arxiv","version":1}},"canonical_sha256":"fb11f6990cc32eef6ac4822c3d2a108d0d9457e30e4dc0c497bda64ce693e0e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb11f6990cc32eef6ac4822c3d2a108d0d9457e30e4dc0c497bda64ce693e0e8","first_computed_at":"2026-07-05T10:00:49.109522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:49.109522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4z1N7VMYV/ha+xFCRkTRsGEbjVj0uJuE0g2hiH1p4EK9MZGT/g4AgF31lTwD3MAAxHmSsR/UMiKRNAv6unvcDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:49.109911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:735e97bbf05e91ec4d9874d46941b525c6e409dbf4a7f3a8e3776ecee6bab7d2","sha256:7c5cb88a8a5b6a711f17469cb5132e2464674fbfa9a417e64b8c48db0eeafd85"],"state_sha256":"af7f933c16b529278c09079e56187f1b3a76ddcd0d26360835b7e180e164d198"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZMsi8p0VvxuojwZaMZWqj2P/c0wStRrDDVUc3Su7uwv+tpUJgl39n0K1fJPMqgilmGZVwmRP8h2BCL0nyH9YDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:14:00.694412Z","bundle_sha256":"956ffea5c5c2d679f22cd78b6a85be64c72470c92ffb3a762078dbbc1c804516"}}