{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OLFKWM63Q337LBYVXGDTYPMC3R","short_pith_number":"pith:OLFKWM63","canonical_record":{"source":{"id":"2412.01293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T09:08:06Z","cross_cats_sorted":[],"title_canon_sha256":"8517932e8380ac7488b4fec024b8f670ca5c2c8930434329557c1f20cd7be1df","abstract_canon_sha256":"3ab7c23e40ccee699f3049557534f07492e753e480d6c4f437983c321c45526e"},"schema_version":"1.0"},"canonical_sha256":"72caab33db86f7f58715b9873c3d82dc7f00803f37160c7eee48c5556cdb6983","source":{"kind":"arxiv","id":"2412.01293","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01293","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01293v1","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01293","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"pith_short_12","alias_value":"OLFKWM63Q337","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"pith_short_16","alias_value":"OLFKWM63Q337LBYV","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"pith_short_8","alias_value":"OLFKWM63","created_at":"2026-07-05T09:42:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OLFKWM63Q337LBYVXGDTYPMC3R","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T09:08:06Z","cross_cats_sorted":[],"title_canon_sha256":"8517932e8380ac7488b4fec024b8f670ca5c2c8930434329557c1f20cd7be1df","abstract_canon_sha256":"3ab7c23e40ccee699f3049557534f07492e753e480d6c4f437983c321c45526e"},"schema_version":"1.0"},"canonical_sha256":"72caab33db86f7f58715b9873c3d82dc7f00803f37160c7eee48c5556cdb6983","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:57.436202Z","signature_b64":"0ZEWpIE5dF5wKpR5JCltZszCAnOmAu6vnucEX6+pYiuUrwBbVJ3BVJeD/vgGim25vWJwR0GcW+ZFEYAfP1zXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72caab33db86f7f58715b9873c3d82dc7f00803f37160c7eee48c5556cdb6983","last_reissued_at":"2026-07-05T09:42:57.435706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:57.435706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01293","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":"2026-07-05T09:42:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00OnCispsryug2sQ9//9B0gH4iv9fiDC7hftMv/gwMU+/+3crqWLPHROrOn4c+uh+ssJlyZkjK3Gk6gzjzjhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:26:45.431512Z"},"content_sha256":"19fd5cf0df8ee992f0dfcc7493d377eb85b2cebab7420c03fd2ce88d6bf1ba83","schema_version":"1.0","event_id":"sha256:19fd5cf0df8ee992f0dfcc7493d377eb85b2cebab7420c03fd2ce88d6bf1ba83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OLFKWM63Q337LBYVXGDTYPMC3R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Himashi Rathnayake, Lahiru De Silva, Ravi Shekhar, Rumesh Sirithunga, Saman Peramuna, Surangika Ranathunga, Thamindu Aluthwala","submitted_at":"2024-12-02T09:08:06Z","abstract_excerpt":"Text Simplification is a task that has been minimally explored for low-resource languages. Consequently, there are only a few manually curated datasets. In this paper, we present a human curated sentence-level text simplification dataset for the Sinhala language. Our evaluation dataset contains 1,000 complex sentences and corresponding 3,000 simplified sentences produced by three different human annotators. We model the text simplification task as a zero-shot and zero resource sequence-to-sequence (seq-seq) task on the multilingual language models mT5 and mBART. We exploit auxiliary data from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01293","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/2412.01293/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":"2026-07-05T09:42:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ixhUfWN29jgjSz72a4h6Ne03MoEl/cEIemoPmV9/kAtIWxvJhOIB0iK1+6sJRy6Tk5MDNOKBtDAX+bs9AhT/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:26:45.432159Z"},"content_sha256":"ead32151fce3505bd8a4e8a2f58db6b9f838db674aac119d8c304cc4dc0fafff","schema_version":"1.0","event_id":"sha256:ead32151fce3505bd8a4e8a2f58db6b9f838db674aac119d8c304cc4dc0fafff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OLFKWM63Q337LBYVXGDTYPMC3R/bundle.json","state_url":"https://pith.science/pith/OLFKWM63Q337LBYVXGDTYPMC3R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OLFKWM63Q337LBYVXGDTYPMC3R/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":"2026-08-13T12:26:45Z","links":{"resolver":"https://pith.science/pith/OLFKWM63Q337LBYVXGDTYPMC3R","bundle":"https://pith.science/pith/OLFKWM63Q337LBYVXGDTYPMC3R/bundle.json","state":"https://pith.science/pith/OLFKWM63Q337LBYVXGDTYPMC3R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OLFKWM63Q337LBYVXGDTYPMC3R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OLFKWM63Q337LBYVXGDTYPMC3R","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":"3ab7c23e40ccee699f3049557534f07492e753e480d6c4f437983c321c45526e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T09:08:06Z","title_canon_sha256":"8517932e8380ac7488b4fec024b8f670ca5c2c8930434329557c1f20cd7be1df"},"schema_version":"1.0","source":{"id":"2412.01293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01293","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01293v1","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01293","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"pith_short_12","alias_value":"OLFKWM63Q337","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"pith_short_16","alias_value":"OLFKWM63Q337LBYV","created_at":"2026-07-05T09:42:57Z"},{"alias_kind":"pith_short_8","alias_value":"OLFKWM63","created_at":"2026-07-05T09:42:57Z"}],"graph_snapshots":[{"event_id":"sha256:ead32151fce3505bd8a4e8a2f58db6b9f838db674aac119d8c304cc4dc0fafff","target":"graph","created_at":"2026-07-05T09:42:57Z","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/2412.01293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text Simplification is a task that has been minimally explored for low-resource languages. Consequently, there are only a few manually curated datasets. In this paper, we present a human curated sentence-level text simplification dataset for the Sinhala language. Our evaluation dataset contains 1,000 complex sentences and corresponding 3,000 simplified sentences produced by three different human annotators. We model the text simplification task as a zero-shot and zero resource sequence-to-sequence (seq-seq) task on the multilingual language models mT5 and mBART. We exploit auxiliary data from ","authors_text":"Himashi Rathnayake, Lahiru De Silva, Ravi Shekhar, Rumesh Sirithunga, Saman Peramuna, Surangika Ranathunga, Thamindu Aluthwala","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T09:08:06Z","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01293","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":"sha256:19fd5cf0df8ee992f0dfcc7493d377eb85b2cebab7420c03fd2ce88d6bf1ba83","target":"record","created_at":"2026-07-05T09:42:57Z","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":"3ab7c23e40ccee699f3049557534f07492e753e480d6c4f437983c321c45526e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T09:08:06Z","title_canon_sha256":"8517932e8380ac7488b4fec024b8f670ca5c2c8930434329557c1f20cd7be1df"},"schema_version":"1.0","source":{"id":"2412.01293","kind":"arxiv","version":1}},"canonical_sha256":"72caab33db86f7f58715b9873c3d82dc7f00803f37160c7eee48c5556cdb6983","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72caab33db86f7f58715b9873c3d82dc7f00803f37160c7eee48c5556cdb6983","first_computed_at":"2026-07-05T09:42:57.435706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:57.435706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ZEWpIE5dF5wKpR5JCltZszCAnOmAu6vnucEX6+pYiuUrwBbVJ3BVJeD/vgGim25vWJwR0GcW+ZFEYAfP1zXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:57.436202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19fd5cf0df8ee992f0dfcc7493d377eb85b2cebab7420c03fd2ce88d6bf1ba83","sha256:ead32151fce3505bd8a4e8a2f58db6b9f838db674aac119d8c304cc4dc0fafff"],"state_sha256":"3b022b57ac459996e42e7900b18bbeb3c91f42d7a2d9130bf950089cb09e676b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oUd97Jxv2EVvWBJhi7I06wPK/Fh0EjJSPWWQfrznszxjKolMRn0ZB+HZ66rUUpPK1AtWgQueiq4o37UsJkAIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T12:26:45.438238Z","bundle_sha256":"ac64406c32a3d0c88bf8832b168a5d8d1955cff460982c4886363edb23bf7e72"}}