{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q654GWMPBWZLQ6MAYAVRDZNFUM","short_pith_number":"pith:Q654GWMP","canonical_record":{"source":{"id":"2408.10441","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T22:31:21Z","cross_cats_sorted":[],"title_canon_sha256":"cfaff8442ceb980a006fc50fc93a4b708612aae88a7708efe032f491ebabf72b","abstract_canon_sha256":"978eaa2eaa28fde83ddabc5c9a4f61f4651f5f53d77ebd501ac33f7787f1d484"},"schema_version":"1.0"},"canonical_sha256":"87bbc3598f0db2b87980c02b11e5a5a311cc560faeb4e7def77451d4df9592b1","source":{"kind":"arxiv","id":"2408.10441","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10441","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10441v3","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10441","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"pith_short_12","alias_value":"Q654GWMPBWZL","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"pith_short_16","alias_value":"Q654GWMPBWZLQ6MA","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"pith_short_8","alias_value":"Q654GWMP","created_at":"2026-06-01T01:02:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q654GWMPBWZLQ6MAYAVRDZNFUM","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10441","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T22:31:21Z","cross_cats_sorted":[],"title_canon_sha256":"cfaff8442ceb980a006fc50fc93a4b708612aae88a7708efe032f491ebabf72b","abstract_canon_sha256":"978eaa2eaa28fde83ddabc5c9a4f61f4651f5f53d77ebd501ac33f7787f1d484"},"schema_version":"1.0"},"canonical_sha256":"87bbc3598f0db2b87980c02b11e5a5a311cc560faeb4e7def77451d4df9592b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:12.808563Z","signature_b64":"yS9dTN3W5Kso5VKnd4N1Evd8QyaBrob9ommjmtJ01srCnYcCqqOdNccPLimIh8culUxlxcGh6Mhxa7w7m05eBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87bbc3598f0db2b87980c02b11e5a5a311cc560faeb4e7def77451d4df9592b1","last_reissued_at":"2026-06-01T01:02:12.807206Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:12.807206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10441","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQ1tUMokFpMgqbEHBeIT7gGHh/KX6/ig+bsQ0E6nWF2VDZ4ufyNBiRDWKPL+t6f9GbhH2hGLuUzbGd6XXOQAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T22:23:50.350140Z"},"content_sha256":"ab424b9430f5f4354ef0072cb7f84aacdcb4894a8a4c435046925bbf08851b7a","schema_version":"1.0","event_id":"sha256:ab424b9430f5f4354ef0072cb7f84aacdcb4894a8a4c435046925bbf08851b7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q654GWMPBWZLQ6MAYAVRDZNFUM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goldfish: Monolingual Language Models for 350 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":"2024-08-19T22:31:21Z","abstract_excerpt":"For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. Despite state-of-the-art performance on reasoning tasks, we find that these models still struggle with basic grammatical text generation in many languages. First, large multilingual models perform worse than bigrams for many languages (e.g. 24% of languages in XGLM 4.5B; 43% in BLOOM 7.1B) using FLORES perplexity as an evaluation metric. Second, when we train small monolingual models with only 125M parameters on 1GB or less data for 350 languages, these sm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10441","kind":"arxiv","version":3},"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/2408.10441/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":"2026-06-01T01:02:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/G2Xik6XBodW4JRHhy/CA2spG9CML4hV/n9s0eSTK2S7SdNKdKezW2sFfP15dsayW9vwAjPduQp5wmSygE8GDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T22:23:50.350857Z"},"content_sha256":"ab835c579c34c34a164dfcfeeba277df994f5166eae0e9ddb26afe5e0e2bc712","schema_version":"1.0","event_id":"sha256:ab835c579c34c34a164dfcfeeba277df994f5166eae0e9ddb26afe5e0e2bc712"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q654GWMPBWZLQ6MAYAVRDZNFUM/bundle.json","state_url":"https://pith.science/pith/Q654GWMPBWZLQ6MAYAVRDZNFUM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q654GWMPBWZLQ6MAYAVRDZNFUM/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":"2026-06-04T22:23:50Z","links":{"resolver":"https://pith.science/pith/Q654GWMPBWZLQ6MAYAVRDZNFUM","bundle":"https://pith.science/pith/Q654GWMPBWZLQ6MAYAVRDZNFUM/bundle.json","state":"https://pith.science/pith/Q654GWMPBWZLQ6MAYAVRDZNFUM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q654GWMPBWZLQ6MAYAVRDZNFUM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q654GWMPBWZLQ6MAYAVRDZNFUM","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":"978eaa2eaa28fde83ddabc5c9a4f61f4651f5f53d77ebd501ac33f7787f1d484","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T22:31:21Z","title_canon_sha256":"cfaff8442ceb980a006fc50fc93a4b708612aae88a7708efe032f491ebabf72b"},"schema_version":"1.0","source":{"id":"2408.10441","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10441","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10441v3","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10441","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"pith_short_12","alias_value":"Q654GWMPBWZL","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"pith_short_16","alias_value":"Q654GWMPBWZLQ6MA","created_at":"2026-06-01T01:02:12Z"},{"alias_kind":"pith_short_8","alias_value":"Q654GWMP","created_at":"2026-06-01T01:02:12Z"}],"graph_snapshots":[{"event_id":"sha256:ab835c579c34c34a164dfcfeeba277df994f5166eae0e9ddb26afe5e0e2bc712","target":"graph","created_at":"2026-06-01T01:02:12Z","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/2408.10441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. Despite state-of-the-art performance on reasoning tasks, we find that these models still struggle with basic grammatical text generation in many languages. First, large multilingual models perform worse than bigrams for many languages (e.g. 24% of languages in XGLM 4.5B; 43% in BLOOM 7.1B) using FLORES perplexity as an evaluation metric. Second, when we train small monolingual models with only 125M parameters on 1GB or less data for 350 languages, these sm","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":"2024-08-19T22:31:21Z","title":"Goldfish: Monolingual Language Models for 350 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10441","kind":"arxiv","version":3},"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:ab424b9430f5f4354ef0072cb7f84aacdcb4894a8a4c435046925bbf08851b7a","target":"record","created_at":"2026-06-01T01:02:12Z","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":"978eaa2eaa28fde83ddabc5c9a4f61f4651f5f53d77ebd501ac33f7787f1d484","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T22:31:21Z","title_canon_sha256":"cfaff8442ceb980a006fc50fc93a4b708612aae88a7708efe032f491ebabf72b"},"schema_version":"1.0","source":{"id":"2408.10441","kind":"arxiv","version":3}},"canonical_sha256":"87bbc3598f0db2b87980c02b11e5a5a311cc560faeb4e7def77451d4df9592b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87bbc3598f0db2b87980c02b11e5a5a311cc560faeb4e7def77451d4df9592b1","first_computed_at":"2026-06-01T01:02:12.807206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:12.807206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yS9dTN3W5Kso5VKnd4N1Evd8QyaBrob9ommjmtJ01srCnYcCqqOdNccPLimIh8culUxlxcGh6Mhxa7w7m05eBQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:12.808563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10441","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab424b9430f5f4354ef0072cb7f84aacdcb4894a8a4c435046925bbf08851b7a","sha256:ab835c579c34c34a164dfcfeeba277df994f5166eae0e9ddb26afe5e0e2bc712"],"state_sha256":"4955aa50d2dad2f60f177816be404084bcb788d36ab105952ed112e6fcfaa4bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QE0eS40e5L514c+Tem//NqNeVb1esNFrNgk6f7y42qzVGJhzrXSXL6CF755SGBaR9+H6FqR6L2vvGlUR6Nk6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T22:23:50.354819Z","bundle_sha256":"606c741220929ae64a47005694babdea5735c39246fbf0ca97d0b76ba3838c70"}}