{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DTBKHQTCKUUYEDRBQ3BLZNVYDH","short_pith_number":"pith:DTBKHQTC","canonical_record":{"source":{"id":"2005.10070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T14:33:33Z","cross_cats_sorted":[],"title_canon_sha256":"61afe68657f74556a84bc10cc1705c0d680e5a5f2956c880687151da8db650e1","abstract_canon_sha256":"a8c6fb62d14764cf43c48614ef5a688fec9e4f62b4f3ac177c2d88f82dde4215"},"schema_version":"1.0"},"canonical_sha256":"1cc2a3c2625529820e2186c2bcb6b819da1c1f9f351a54ff46d4496d60b84d67","source":{"kind":"arxiv","id":"2005.10070","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.10070","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2005.10070v1","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10070","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"DTBKHQTCKUUY","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"DTBKHQTCKUUYEDRB","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"DTBKHQTC","created_at":"2026-07-05T01:04:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DTBKHQTCKUUYEDRBQ3BLZNVYDH","target":"record","payload":{"canonical_record":{"source":{"id":"2005.10070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T14:33:33Z","cross_cats_sorted":[],"title_canon_sha256":"61afe68657f74556a84bc10cc1705c0d680e5a5f2956c880687151da8db650e1","abstract_canon_sha256":"a8c6fb62d14764cf43c48614ef5a688fec9e4f62b4f3ac177c2d88f82dde4215"},"schema_version":"1.0"},"canonical_sha256":"1cc2a3c2625529820e2186c2bcb6b819da1c1f9f351a54ff46d4496d60b84d67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:04:36.699819Z","signature_b64":"ye4d/AdfvSFgUlMz+TImJUDVKnj+Rum81IfGg/fmN7LPDhPMUMG9G5+t2LCv0ZSYYuPDvkoZBXqDCQJ6JnNDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cc2a3c2625529820e2186c2bcb6b819da1c1f9f351a54ff46d4496d60b84d67","last_reissued_at":"2026-07-05T01:04:36.699349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:04:36.699349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.10070","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":"2026-07-05T01:04:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bksjEKPH5dFLjQVg75cRrbjoi1D6EO2uhBUvZsgZZV9W5fr2vFvHKAd24OTQG/WGqljSoKV6+9egFpZbkLIVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T03:32:58.630723Z"},"content_sha256":"66b69243ed50ea5f6c9397581bc2c180e1c67af1debbeb75ba6009771facf3ce","schema_version":"1.0","event_id":"sha256:66b69243ed50ea5f6c9397581bc2c180e1c67af1debbeb75ba6009771facf3ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DTBKHQTCKUUYEDRBQ3BLZNVYDH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Hokamp, Demian Gholipour Ghalandari, Georgiana Ifrim, John Glover, Nghia The Pham","submitted_at":"2020-05-20T14:33:33Z","abstract_excerpt":"Multi-document summarization (MDS) aims to compress the content in large document collections into short summaries and has important applications in story clustering for newsfeeds, presentation of search results, and timeline generation. However, there is a lack of datasets that realistically address such use cases at a scale large enough for training supervised models for this task. This work presents a new dataset for MDS that is large both in the total number of document clusters and in the size of individual clusters. We build this dataset by leveraging the Wikipedia Current Events Portal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10070","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/2005.10070/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":"2026-07-05T01:04:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QnR/7SXMatlJCYgtkHAnWOTNhfh0RWVqqbjacSioUthUWu8e9KTO8NR6RJ78sNHGVoqBnHqyeYGcwbZwWH6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T03:32:58.631281Z"},"content_sha256":"e34848f4810ee3f86a55c20237aa7ea0cff409abb62c6a3d1730d582b07a6cc4","schema_version":"1.0","event_id":"sha256:e34848f4810ee3f86a55c20237aa7ea0cff409abb62c6a3d1730d582b07a6cc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DTBKHQTCKUUYEDRBQ3BLZNVYDH/bundle.json","state_url":"https://pith.science/pith/DTBKHQTCKUUYEDRBQ3BLZNVYDH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DTBKHQTCKUUYEDRBQ3BLZNVYDH/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":"2026-08-23T03:32:58Z","links":{"resolver":"https://pith.science/pith/DTBKHQTCKUUYEDRBQ3BLZNVYDH","bundle":"https://pith.science/pith/DTBKHQTCKUUYEDRBQ3BLZNVYDH/bundle.json","state":"https://pith.science/pith/DTBKHQTCKUUYEDRBQ3BLZNVYDH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DTBKHQTCKUUYEDRBQ3BLZNVYDH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DTBKHQTCKUUYEDRBQ3BLZNVYDH","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":"a8c6fb62d14764cf43c48614ef5a688fec9e4f62b4f3ac177c2d88f82dde4215","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T14:33:33Z","title_canon_sha256":"61afe68657f74556a84bc10cc1705c0d680e5a5f2956c880687151da8db650e1"},"schema_version":"1.0","source":{"id":"2005.10070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.10070","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2005.10070v1","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10070","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"DTBKHQTCKUUY","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"DTBKHQTCKUUYEDRB","created_at":"2026-07-05T01:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"DTBKHQTC","created_at":"2026-07-05T01:04:36Z"}],"graph_snapshots":[{"event_id":"sha256:e34848f4810ee3f86a55c20237aa7ea0cff409abb62c6a3d1730d582b07a6cc4","target":"graph","created_at":"2026-07-05T01:04:36Z","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/2005.10070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-document summarization (MDS) aims to compress the content in large document collections into short summaries and has important applications in story clustering for newsfeeds, presentation of search results, and timeline generation. However, there is a lack of datasets that realistically address such use cases at a scale large enough for training supervised models for this task. This work presents a new dataset for MDS that is large both in the total number of document clusters and in the size of individual clusters. We build this dataset by leveraging the Wikipedia Current Events Portal ","authors_text":"Chris Hokamp, Demian Gholipour Ghalandari, Georgiana Ifrim, John Glover, Nghia The Pham","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T14:33:33Z","title":"A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10070","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":"sha256:66b69243ed50ea5f6c9397581bc2c180e1c67af1debbeb75ba6009771facf3ce","target":"record","created_at":"2026-07-05T01:04:36Z","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":"a8c6fb62d14764cf43c48614ef5a688fec9e4f62b4f3ac177c2d88f82dde4215","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T14:33:33Z","title_canon_sha256":"61afe68657f74556a84bc10cc1705c0d680e5a5f2956c880687151da8db650e1"},"schema_version":"1.0","source":{"id":"2005.10070","kind":"arxiv","version":1}},"canonical_sha256":"1cc2a3c2625529820e2186c2bcb6b819da1c1f9f351a54ff46d4496d60b84d67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cc2a3c2625529820e2186c2bcb6b819da1c1f9f351a54ff46d4496d60b84d67","first_computed_at":"2026-07-05T01:04:36.699349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:04:36.699349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ye4d/AdfvSFgUlMz+TImJUDVKnj+Rum81IfGg/fmN7LPDhPMUMG9G5+t2LCv0ZSYYuPDvkoZBXqDCQJ6JnNDCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:04:36.699819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.10070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66b69243ed50ea5f6c9397581bc2c180e1c67af1debbeb75ba6009771facf3ce","sha256:e34848f4810ee3f86a55c20237aa7ea0cff409abb62c6a3d1730d582b07a6cc4"],"state_sha256":"0d621dd6753e4d8fefee339e3f19b65b38dab13c019668fe4794d81ae7c546e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pd8OwfYBJVowHe+KVi0x2qXqrydcN/qHnGZErSRcPG3fo5jkIpAbRxwagV7ZBt5bfeGLBio1QOm2sLXcFnNSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T03:32:58.635107Z","bundle_sha256":"daa12fb115ca39bcde28fe66b897908d0fb68732ebf17a4a7874c267dcd0f133"}}