{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GHJMPXU7JV6T634FYDMWDSLH4Q","short_pith_number":"pith:GHJMPXU7","schema_version":"1.0","canonical_sha256":"31d2c7de9f4d7d3f6f85c0d961c967e41d137ec31ab84937be9ed07242baae81","source":{"kind":"arxiv","id":"2212.09674","version":2},"attestation_state":"computed","paper":{"title":"LR-Sum: Summarization for Less-Resourced Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chester Palen-Michel, Constantine Lignos","submitted_at":"2022-12-19T18:00:09Z","abstract_excerpt":"This preprint describes work in progress on LR-Sum, a new permissively-licensed dataset created with the goal of enabling further research in automatic summarization for less-resourced languages. LR-Sum contains human-written summaries for 40 languages, many of which are less-resourced. We describe our process for extracting and filtering the dataset from the Multilingual Open Text corpus (Palen-Michel et al., 2022). The source data is public domain newswire collected from from Voice of America websites, and LR-Sum is released under a Creative Commons license (CC BY 4.0), making it one of the "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2212.09674","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T18:00:09Z","cross_cats_sorted":[],"title_canon_sha256":"a2a6ac424243e5abbefa9b0643b750315a47b200f6565aeffe5fa83f919792c4","abstract_canon_sha256":"dd72f663980ccf7c80cd030d3a6a00016167d3597d48aa33e9a9636cbb55a7a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:40.862548Z","signature_b64":"bbXmjeaLV5J7rcMbYuccQEIX6wnc+prU/eMf29D3e28r+8+eb3yzceNWJrJNvLiIfWj1KREYG6Bj/rgJ8OBWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d2c7de9f4d7d3f6f85c0d961c967e41d137ec31ab84937be9ed07242baae81","last_reissued_at":"2026-07-05T07:05:40.861979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:40.861979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LR-Sum: Summarization for Less-Resourced Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chester Palen-Michel, Constantine Lignos","submitted_at":"2022-12-19T18:00:09Z","abstract_excerpt":"This preprint describes work in progress on LR-Sum, a new permissively-licensed dataset created with the goal of enabling further research in automatic summarization for less-resourced languages. LR-Sum contains human-written summaries for 40 languages, many of which are less-resourced. We describe our process for extracting and filtering the dataset from the Multilingual Open Text corpus (Palen-Michel et al., 2022). The source data is public domain newswire collected from from Voice of America websites, and LR-Sum is released under a Creative Commons license (CC BY 4.0), making it one of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09674","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/2212.09674/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2212.09674","created_at":"2026-07-05T07:05:40.862033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09674v2","created_at":"2026-07-05T07:05:40.862033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09674","created_at":"2026-07-05T07:05:40.862033+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHJMPXU7JV6T","created_at":"2026-07-05T07:05:40.862033+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHJMPXU7JV6T634F","created_at":"2026-07-05T07:05:40.862033+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHJMPXU7","created_at":"2026-07-05T07:05:40.862033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q","json":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q.json","graph_json":"https://pith.science/api/pith-number/GHJMPXU7JV6T634FYDMWDSLH4Q/graph.json","events_json":"https://pith.science/api/pith-number/GHJMPXU7JV6T634FYDMWDSLH4Q/events.json","paper":"https://pith.science/paper/GHJMPXU7"},"agent_actions":{"view_html":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q","download_json":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q.json","view_paper":"https://pith.science/paper/GHJMPXU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09674&json=true","fetch_graph":"https://pith.science/api/pith-number/GHJMPXU7JV6T634FYDMWDSLH4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/GHJMPXU7JV6T634FYDMWDSLH4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q/action/storage_attestation","attest_author":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q/action/author_attestation","sign_citation":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q/action/citation_signature","submit_replication":"https://pith.science/pith/GHJMPXU7JV6T634FYDMWDSLH4Q/action/replication_record"}},"created_at":"2026-07-05T07:05:40.862033+00:00","updated_at":"2026-07-05T07:05:40.862033+00:00"}