{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NMAOYGL765BUOQCMNNTFEOTJMT","short_pith_number":"pith:NMAOYGL7","canonical_record":{"source":{"id":"2106.13822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T18:00:24Z","cross_cats_sorted":[],"title_canon_sha256":"80699194a0db2188d560dad5b61a8b5a2e5eae03566283b5ecf653b5a95288c2","abstract_canon_sha256":"27772921a67ae0abbe09c4bbe9b952ba937b3f947574f5c4feea43749a31f69c"},"schema_version":"1.0"},"canonical_sha256":"6b00ec197ff74347404c6b66523a6964efc18fcdcbc029118c2ee7434b721581","source":{"kind":"arxiv","id":"2106.13822","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13822","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13822v1","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13822","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"NMAOYGL765BU","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_16","alias_value":"NMAOYGL765BUOQCM","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_8","alias_value":"NMAOYGL7","created_at":"2026-07-05T02:52:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NMAOYGL765BUOQCMNNTFEOTJMT","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T18:00:24Z","cross_cats_sorted":[],"title_canon_sha256":"80699194a0db2188d560dad5b61a8b5a2e5eae03566283b5ecf653b5a95288c2","abstract_canon_sha256":"27772921a67ae0abbe09c4bbe9b952ba937b3f947574f5c4feea43749a31f69c"},"schema_version":"1.0"},"canonical_sha256":"6b00ec197ff74347404c6b66523a6964efc18fcdcbc029118c2ee7434b721581","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:28.967222Z","signature_b64":"HoixbRGz0dCgQPVwpXGF5mR+bNs9VzcV4iOFrijwYqoBVPikC9dqc4sdtZifwzd42VSQv03DXyRym5pYhBc4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b00ec197ff74347404c6b66523a6964efc18fcdcbc029118c2ee7434b721581","last_reissued_at":"2026-07-05T02:52:28.966774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:28.966774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13822","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":"2026-07-05T02:52:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z6EDyszwDNHYUE//nxP0ccpPNvQ1iit6wdOlvfgMKe9B+N/L1IByREebtKFzD9ZY4UEBfrU/dnGjtcP1AFXqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:03:49.496842Z"},"content_sha256":"ab51a374aacc0ff22adf0ad784d39bb5f64af6edb85e8d054e8bc6cdac1757de","schema_version":"1.0","event_id":"sha256:ab51a374aacc0ff22adf0ad784d39bb5f64af6edb85e8d054e8bc6cdac1757de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NMAOYGL765BUOQCMNNTFEOTJMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhik Bhattacharjee, Kazi Samin, Md Saiful Islam, M. Sohel Rahman, Rifat Shahriyar, Tahmid Hasan, Yong-Bin Kang, Yuan-Fang Li","submitted_at":"2021-06-25T18:00:24Z","abstract_excerpt":"Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public dataset is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13822","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/2106.13822/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":"2026-07-05T02:52:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NEUMxgcziWsyuqBB3JDIhCOxFlCUKifBGcg2r2TGCp+3cS2Xuz8wbE+rOUfwIdcC/uopdno9jwvkPhPI5eJXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:03:49.497394Z"},"content_sha256":"991f6813029adef853c30cb6cb0819575b0466c880a168c7380878cf42c413ec","schema_version":"1.0","event_id":"sha256:991f6813029adef853c30cb6cb0819575b0466c880a168c7380878cf42c413ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/bundle.json","state_url":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMAOYGL765BUOQCMNNTFEOTJMT/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":"2026-08-05T06:03:49Z","links":{"resolver":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT","bundle":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/bundle.json","state":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMAOYGL765BUOQCMNNTFEOTJMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NMAOYGL765BUOQCMNNTFEOTJMT","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":"27772921a67ae0abbe09c4bbe9b952ba937b3f947574f5c4feea43749a31f69c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T18:00:24Z","title_canon_sha256":"80699194a0db2188d560dad5b61a8b5a2e5eae03566283b5ecf653b5a95288c2"},"schema_version":"1.0","source":{"id":"2106.13822","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13822","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13822v1","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13822","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"NMAOYGL765BU","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_16","alias_value":"NMAOYGL765BUOQCM","created_at":"2026-07-05T02:52:28Z"},{"alias_kind":"pith_short_8","alias_value":"NMAOYGL7","created_at":"2026-07-05T02:52:28Z"}],"graph_snapshots":[{"event_id":"sha256:991f6813029adef853c30cb6cb0819575b0466c880a168c7380878cf42c413ec","target":"graph","created_at":"2026-07-05T02:52:28Z","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/2106.13822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public dataset is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by","authors_text":"Abhik Bhattacharjee, Kazi Samin, Md Saiful Islam, M. Sohel Rahman, Rifat Shahriyar, Tahmid Hasan, Yong-Bin Kang, Yuan-Fang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T18:00:24Z","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13822","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:ab51a374aacc0ff22adf0ad784d39bb5f64af6edb85e8d054e8bc6cdac1757de","target":"record","created_at":"2026-07-05T02:52:28Z","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":"27772921a67ae0abbe09c4bbe9b952ba937b3f947574f5c4feea43749a31f69c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T18:00:24Z","title_canon_sha256":"80699194a0db2188d560dad5b61a8b5a2e5eae03566283b5ecf653b5a95288c2"},"schema_version":"1.0","source":{"id":"2106.13822","kind":"arxiv","version":1}},"canonical_sha256":"6b00ec197ff74347404c6b66523a6964efc18fcdcbc029118c2ee7434b721581","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b00ec197ff74347404c6b66523a6964efc18fcdcbc029118c2ee7434b721581","first_computed_at":"2026-07-05T02:52:28.966774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:28.966774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HoixbRGz0dCgQPVwpXGF5mR+bNs9VzcV4iOFrijwYqoBVPikC9dqc4sdtZifwzd42VSQv03DXyRym5pYhBc4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:28.967222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13822","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab51a374aacc0ff22adf0ad784d39bb5f64af6edb85e8d054e8bc6cdac1757de","sha256:991f6813029adef853c30cb6cb0819575b0466c880a168c7380878cf42c413ec"],"state_sha256":"0eeed9068dba9c96028e3fc32a55b94982a0a77679ba83ac60a734a648d8e825"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zi9AQTNIto7jp9E97cFAeOBU+7tSuZXs9b/pGBPoD7THeWJlYhtpP8ULtVT6lPn/7hUfULNrMta/l4ddGDiCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:03:49.538201Z","bundle_sha256":"2c586e2b36856cd835a7694c5d8a05dac0b14f96cf3e225cc1e4fd03166a730b"}}