{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:J6HSTRM5ALOO2FYEVUD4ITMA7F","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":"b2b4355fda1d5787489901712a7f1c667d6d5b041d16c149ebbeb0a3f9d7e47d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T09:01:39Z","title_canon_sha256":"c4e4144ed1e26ed08d832f13d3ab63557d99dc5396235d458900ba4d30ab0a33"},"schema_version":"1.0","source":{"id":"2101.00406","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00406","created_at":"2026-07-05T03:11:11Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00406v2","created_at":"2026-07-05T03:11:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00406","created_at":"2026-07-05T03:11:11Z"},{"alias_kind":"pith_short_12","alias_value":"J6HSTRM5ALOO","created_at":"2026-07-05T03:11:11Z"},{"alias_kind":"pith_short_16","alias_value":"J6HSTRM5ALOO2FYE","created_at":"2026-07-05T03:11:11Z"},{"alias_kind":"pith_short_8","alias_value":"J6HSTRM5","created_at":"2026-07-05T03:11:11Z"}],"graph_snapshots":[{"event_id":"sha256:425048845b4d776c6a505efa792526fdd80a1eef9442a644900e1cad67c5f1f6","target":"graph","created_at":"2026-07-05T03:11:11Z","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/2101.00406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a new pretraining approach geared for multi-document language modeling, incorporating two key ideas into the masked language modeling self-supervised objective. First, instead of considering documents in isolation, we pretrain over sets of multiple related documents, encouraging the model to learn cross-document relationships. Second, we improve over recent long-range transformers by introducing dynamic global attention that has access to the entire input to predict masked tokens. We release CDLM (Cross-Document Language Model), a new general language model for multi-document sett","authors_text":"Arie Cattan, Arman Cohan, Avi Caciularu, Ido Dagan, Iz Beltagy, Matthew E. Peters","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T09:01:39Z","title":"CDLM: Cross-Document Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00406","kind":"arxiv","version":2},"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":"sha256:26bda3f5896d5033016f4b41d4dd9d8ecb692258efaac8cff3cde8ef3d28ae92","target":"record","created_at":"2026-07-05T03:11:11Z","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":"b2b4355fda1d5787489901712a7f1c667d6d5b041d16c149ebbeb0a3f9d7e47d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T09:01:39Z","title_canon_sha256":"c4e4144ed1e26ed08d832f13d3ab63557d99dc5396235d458900ba4d30ab0a33"},"schema_version":"1.0","source":{"id":"2101.00406","kind":"arxiv","version":2}},"canonical_sha256":"4f8f29c59d02dced1704ad07c44d80f94b2f51b16c40d297d2d2ced531d3a451","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f8f29c59d02dced1704ad07c44d80f94b2f51b16c40d297d2d2ced531d3a451","first_computed_at":"2026-07-05T03:11:11.409542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:11.409542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qy4I/jzDJ8jauHbLifhgTwzVL6D8Dw61dle/1EndQPZotFZMtNsb5YHxCTvVVI4OVXA96jTalQSLdmt2APvBAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:11.409985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00406","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26bda3f5896d5033016f4b41d4dd9d8ecb692258efaac8cff3cde8ef3d28ae92","sha256:425048845b4d776c6a505efa792526fdd80a1eef9442a644900e1cad67c5f1f6"],"state_sha256":"da2a7087ad06e5cd0132d699a9a80e47b8f3ab880a7afdda3adfe26b0565a4ed"}