{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4CDT5YXMQVVF4FDIRH3JU5BN6J","short_pith_number":"pith:4CDT5YXM","canonical_record":{"source":{"id":"2204.07580","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T13:02:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8e163858d9d0b110bcc72dcb61a3e9f3b159704b9f692d637074532d0d6d6bcc","abstract_canon_sha256":"631b10ba1d5376eb60a70ced212974a55f90267266de21875bfbb5ca91c62a9e"},"schema_version":"1.0"},"canonical_sha256":"e0873ee2ec856a5e146889f69a742df270b4c6b115722ff2fef5f66c2d208441","source":{"kind":"arxiv","id":"2204.07580","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07580","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07580v2","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07580","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"pith_short_12","alias_value":"4CDT5YXMQVVF","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"pith_short_16","alias_value":"4CDT5YXMQVVF4FDI","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"pith_short_8","alias_value":"4CDT5YXM","created_at":"2026-07-05T07:00:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4CDT5YXMQVVF4FDIRH3JU5BN6J","target":"record","payload":{"canonical_record":{"source":{"id":"2204.07580","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T13:02:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8e163858d9d0b110bcc72dcb61a3e9f3b159704b9f692d637074532d0d6d6bcc","abstract_canon_sha256":"631b10ba1d5376eb60a70ced212974a55f90267266de21875bfbb5ca91c62a9e"},"schema_version":"1.0"},"canonical_sha256":"e0873ee2ec856a5e146889f69a742df270b4c6b115722ff2fef5f66c2d208441","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:06.041015Z","signature_b64":"Db3W5nbpk7bqTT2gudds3IXen0hUR3wJS/3F8tvgIhBeGLSCVEs270BDz3NovGwAqVSkZ3xwl70B2dVUIgbkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0873ee2ec856a5e146889f69a742df270b4c6b115722ff2fef5f66c2d208441","last_reissued_at":"2026-07-05T07:00:06.040536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:06.040536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.07580","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SyuR3c6BMmlBAWTa85IspC/hQaA58xJNNc98RDnLH21JN5S6NnwgBrqjtjDZDY0vyl91O2krxmzoMlyHSwaYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:52:16.581370Z"},"content_sha256":"e98ecbde38b807d02c5eefac371c764f7e4e327a04bc680b76c57601db2566ac","schema_version":"1.0","event_id":"sha256:e98ecbde38b807d02c5eefac371c764f7e4e327a04bc680b76c57601db2566ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4CDT5YXMQVVF4FDIRH3JU5BN6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"mGPT: Few-Shot Learners Go Multilingual","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alena Fenogenova, Anastasia Kozlova, Maria Tikhonova, Oleh Shliazhko, Tatiana Shavrina, Vladislav Mikhailov","submitted_at":"2022-04-15T13:02:33Z","abstract_excerpt":"Recent studies report that autoregressive language models can successfully solve many NLP tasks via zero- and few-shot learning paradigms, which opens up new possibilities for using the pre-trained language models. This paper introduces two autoregressive GPT-like models with 1.3 billion and 13 billion parameters trained on 60 languages from 25 language families using Wikipedia and Colossal Clean Crawled Corpus. We reproduce the GPT-3 architecture using GPT-2 sources and the sparse attention mechanism; Deepspeed and Megatron frameworks allow us to parallelize the training and inference steps e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07580","kind":"arxiv","version":2},"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/2204.07580/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":"2026-07-05T07:00:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r27YFit6MJjdo5oyhGERS5xxKxyvYfEsdFQpkypn7nr7yk7yWSX/WihVYSgo2KEmaNP9BA/vuGP8bYOtXeYiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:52:16.582001Z"},"content_sha256":"3dae1c8e72215e50eaaae70ca1b9b271c1f12158b7abf158fa3bbb125fd982bf","schema_version":"1.0","event_id":"sha256:3dae1c8e72215e50eaaae70ca1b9b271c1f12158b7abf158fa3bbb125fd982bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4CDT5YXMQVVF4FDIRH3JU5BN6J/bundle.json","state_url":"https://pith.science/pith/4CDT5YXMQVVF4FDIRH3JU5BN6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4CDT5YXMQVVF4FDIRH3JU5BN6J/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":"2026-07-07T00:52:16Z","links":{"resolver":"https://pith.science/pith/4CDT5YXMQVVF4FDIRH3JU5BN6J","bundle":"https://pith.science/pith/4CDT5YXMQVVF4FDIRH3JU5BN6J/bundle.json","state":"https://pith.science/pith/4CDT5YXMQVVF4FDIRH3JU5BN6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4CDT5YXMQVVF4FDIRH3JU5BN6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4CDT5YXMQVVF4FDIRH3JU5BN6J","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":"631b10ba1d5376eb60a70ced212974a55f90267266de21875bfbb5ca91c62a9e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T13:02:33Z","title_canon_sha256":"8e163858d9d0b110bcc72dcb61a3e9f3b159704b9f692d637074532d0d6d6bcc"},"schema_version":"1.0","source":{"id":"2204.07580","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07580","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07580v2","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07580","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"pith_short_12","alias_value":"4CDT5YXMQVVF","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"pith_short_16","alias_value":"4CDT5YXMQVVF4FDI","created_at":"2026-07-05T07:00:06Z"},{"alias_kind":"pith_short_8","alias_value":"4CDT5YXM","created_at":"2026-07-05T07:00:06Z"}],"graph_snapshots":[{"event_id":"sha256:3dae1c8e72215e50eaaae70ca1b9b271c1f12158b7abf158fa3bbb125fd982bf","target":"graph","created_at":"2026-07-05T07:00:06Z","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/2204.07580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies report that autoregressive language models can successfully solve many NLP tasks via zero- and few-shot learning paradigms, which opens up new possibilities for using the pre-trained language models. This paper introduces two autoregressive GPT-like models with 1.3 billion and 13 billion parameters trained on 60 languages from 25 language families using Wikipedia and Colossal Clean Crawled Corpus. We reproduce the GPT-3 architecture using GPT-2 sources and the sparse attention mechanism; Deepspeed and Megatron frameworks allow us to parallelize the training and inference steps e","authors_text":"Alena Fenogenova, Anastasia Kozlova, Maria Tikhonova, Oleh Shliazhko, Tatiana Shavrina, Vladislav Mikhailov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T13:02:33Z","title":"mGPT: Few-Shot Learners Go Multilingual"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07580","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:e98ecbde38b807d02c5eefac371c764f7e4e327a04bc680b76c57601db2566ac","target":"record","created_at":"2026-07-05T07:00:06Z","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":"631b10ba1d5376eb60a70ced212974a55f90267266de21875bfbb5ca91c62a9e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T13:02:33Z","title_canon_sha256":"8e163858d9d0b110bcc72dcb61a3e9f3b159704b9f692d637074532d0d6d6bcc"},"schema_version":"1.0","source":{"id":"2204.07580","kind":"arxiv","version":2}},"canonical_sha256":"e0873ee2ec856a5e146889f69a742df270b4c6b115722ff2fef5f66c2d208441","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0873ee2ec856a5e146889f69a742df270b4c6b115722ff2fef5f66c2d208441","first_computed_at":"2026-07-05T07:00:06.040536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:06.040536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Db3W5nbpk7bqTT2gudds3IXen0hUR3wJS/3F8tvgIhBeGLSCVEs270BDz3NovGwAqVSkZ3xwl70B2dVUIgbkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:06.041015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.07580","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e98ecbde38b807d02c5eefac371c764f7e4e327a04bc680b76c57601db2566ac","sha256:3dae1c8e72215e50eaaae70ca1b9b271c1f12158b7abf158fa3bbb125fd982bf"],"state_sha256":"e53213ee2903c32e08ce587955a235b24233a843a405a61d69b8e01fc7be949b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4OfFDJGdLW/v7SQQ0JeZPZivnW1PO2cg3xhHIeImXkezoVQKefRW1DYDmXKGAcgl8dQV2HgmRrTiTQqAtNJjBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T00:52:16.585167Z","bundle_sha256":"423c80dccbf999ca1aeedda4815cda0e45307b86009ba9eaddec2593c4ce4f20"}}