{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XEVZEA2GT247BO2IFPZMKVMYAE","short_pith_number":"pith:XEVZEA2G","canonical_record":{"source":{"id":"2311.09205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T18:47:42Z","cross_cats_sorted":[],"title_canon_sha256":"b54d10f532a7382924d895c010be2a6c37c3d9b02ad9b22ede0a6dd5c63ddca8","abstract_canon_sha256":"dba8e761e9d6a274ee87990d059ba65c909c83920a76ec93d8587165f33a1da0"},"schema_version":"1.0"},"canonical_sha256":"b92b9203469eb9f0bb482bf2c555980126fd75d1819f1bbf025ed541bea201f7","source":{"kind":"arxiv","id":"2311.09205","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09205","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09205v1","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09205","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"XEVZEA2GT247","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"XEVZEA2GT247BO2I","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"XEVZEA2G","created_at":"2026-07-05T07:13:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XEVZEA2GT247BO2IFPZMKVMYAE","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T18:47:42Z","cross_cats_sorted":[],"title_canon_sha256":"b54d10f532a7382924d895c010be2a6c37c3d9b02ad9b22ede0a6dd5c63ddca8","abstract_canon_sha256":"dba8e761e9d6a274ee87990d059ba65c909c83920a76ec93d8587165f33a1da0"},"schema_version":"1.0"},"canonical_sha256":"b92b9203469eb9f0bb482bf2c555980126fd75d1819f1bbf025ed541bea201f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:10.206280Z","signature_b64":"bPwC9D4NpnjIfLLaJAnaN3TclCx9iQBc+pscPM3A36BJnazt7zEVlYiX3LV0JGmdL7A1E6FBF4LK17/Rj7kyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b92b9203469eb9f0bb482bf2c555980126fd75d1819f1bbf025ed541bea201f7","last_reissued_at":"2026-07-05T07:13:10.205767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:10.205767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09205","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":"2026-07-05T07:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/oEt796KzW/Q/KhlTkq3b7kbJLJSO7mTTqw3CIFO0+9/4SEoz8rxIJpj18pb/DoWLYN0ZiorjB3dLaUj8bBTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:16:39.359139Z"},"content_sha256":"d1f460134dd5e07f8b645c6e36af5a9cfc0e185a4cc9b81e86429baae6a4fa53","schema_version":"1.0","event_id":"sha256:d1f460134dd5e07f8b645c6e36af5a9cfc0e185a4cc9b81e86429baae6a4fa53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XEVZEA2GT247BO2IFPZMKVMYAE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin K. Bergen, Catherine Arnett, Tyler A. Chang, Zhuowen Tu","submitted_at":"2023-11-15T18:47:42Z","abstract_excerpt":"Multilingual language models are widely used to extend NLP systems to low-resource languages. However, concrete evidence for the effects of multilinguality on language modeling performance in individual languages remains scarce. Here, we pre-train over 10,000 monolingual and multilingual language models for over 250 languages, including multiple language families that are under-studied in NLP. We assess how language modeling performance in each language varies as a function of (1) monolingual dataset size, (2) added multilingual dataset size, (3) linguistic similarity of the added languages, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09205","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/2311.09205/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":"2026-07-05T07:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Amk/0gRMqVsZQQygPexsU2D9TmEt3ttAuODH5lkR9o2UOlMt76MF6G9VoozKuwrOA+o3f3PeDyv8t1zxcIxLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:16:39.359645Z"},"content_sha256":"be31e17f00f630941fb4b7585ee5a3f555d10111b432af808c52e95a9a09d385","schema_version":"1.0","event_id":"sha256:be31e17f00f630941fb4b7585ee5a3f555d10111b432af808c52e95a9a09d385"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XEVZEA2GT247BO2IFPZMKVMYAE/bundle.json","state_url":"https://pith.science/pith/XEVZEA2GT247BO2IFPZMKVMYAE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XEVZEA2GT247BO2IFPZMKVMYAE/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":"2026-08-08T09:16:39Z","links":{"resolver":"https://pith.science/pith/XEVZEA2GT247BO2IFPZMKVMYAE","bundle":"https://pith.science/pith/XEVZEA2GT247BO2IFPZMKVMYAE/bundle.json","state":"https://pith.science/pith/XEVZEA2GT247BO2IFPZMKVMYAE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XEVZEA2GT247BO2IFPZMKVMYAE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XEVZEA2GT247BO2IFPZMKVMYAE","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":"dba8e761e9d6a274ee87990d059ba65c909c83920a76ec93d8587165f33a1da0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T18:47:42Z","title_canon_sha256":"b54d10f532a7382924d895c010be2a6c37c3d9b02ad9b22ede0a6dd5c63ddca8"},"schema_version":"1.0","source":{"id":"2311.09205","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09205","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09205v1","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09205","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"XEVZEA2GT247","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"XEVZEA2GT247BO2I","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"XEVZEA2G","created_at":"2026-07-05T07:13:10Z"}],"graph_snapshots":[{"event_id":"sha256:be31e17f00f630941fb4b7585ee5a3f555d10111b432af808c52e95a9a09d385","target":"graph","created_at":"2026-07-05T07:13:10Z","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/2311.09205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual language models are widely used to extend NLP systems to low-resource languages. However, concrete evidence for the effects of multilinguality on language modeling performance in individual languages remains scarce. Here, we pre-train over 10,000 monolingual and multilingual language models for over 250 languages, including multiple language families that are under-studied in NLP. We assess how language modeling performance in each language varies as a function of (1) monolingual dataset size, (2) added multilingual dataset size, (3) linguistic similarity of the added languages, a","authors_text":"Benjamin K. Bergen, Catherine Arnett, Tyler A. Chang, Zhuowen Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T18:47:42Z","title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09205","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:d1f460134dd5e07f8b645c6e36af5a9cfc0e185a4cc9b81e86429baae6a4fa53","target":"record","created_at":"2026-07-05T07:13:10Z","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":"dba8e761e9d6a274ee87990d059ba65c909c83920a76ec93d8587165f33a1da0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T18:47:42Z","title_canon_sha256":"b54d10f532a7382924d895c010be2a6c37c3d9b02ad9b22ede0a6dd5c63ddca8"},"schema_version":"1.0","source":{"id":"2311.09205","kind":"arxiv","version":1}},"canonical_sha256":"b92b9203469eb9f0bb482bf2c555980126fd75d1819f1bbf025ed541bea201f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b92b9203469eb9f0bb482bf2c555980126fd75d1819f1bbf025ed541bea201f7","first_computed_at":"2026-07-05T07:13:10.205767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:10.205767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bPwC9D4NpnjIfLLaJAnaN3TclCx9iQBc+pscPM3A36BJnazt7zEVlYiX3LV0JGmdL7A1E6FBF4LK17/Rj7kyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:10.206280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09205","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1f460134dd5e07f8b645c6e36af5a9cfc0e185a4cc9b81e86429baae6a4fa53","sha256:be31e17f00f630941fb4b7585ee5a3f555d10111b432af808c52e95a9a09d385"],"state_sha256":"257e2d86efbb93ca3c354bd5a92915f6433f8bfbac29a433b9ece1068930acb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjvwoLzsbFqKGqqLpTjuGDE96JlSyX19jWHY81USmNrobQMOKSGou/VjUP9AQNKLT6jF6nduPXUzxNQth7sVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:16:39.364076Z","bundle_sha256":"ff687771cfdc9f751bc5ef69fac6111ce70c47cb6432d76136d93c200536216c"}}