{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OHZV4R4GGF7IM5FBCYRDOY6O3P","short_pith_number":"pith:OHZV4R4G","canonical_record":{"source":{"id":"2202.03371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-07T17:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"655f49714970a3adda6215c483a764b9528ff77f47a2bcf749372a5cbf1bc74a","abstract_canon_sha256":"5d37aad78d599a067400246f3fbce9efe8b932679571f4f76cfb2a37cd2a1a92"},"schema_version":"1.0"},"canonical_sha256":"71f35e4786317e8674a116223763cedbc615cb54559d9ccfdb4bfb39143dcc63","source":{"kind":"arxiv","id":"2202.03371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03371","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03371v1","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03371","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"OHZV4R4GGF7I","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"OHZV4R4GGF7IM5FB","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"OHZV4R4G","created_at":"2026-07-05T03:54:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OHZV4R4GGF7IM5FBCYRDOY6O3P","target":"record","payload":{"canonical_record":{"source":{"id":"2202.03371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-07T17:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"655f49714970a3adda6215c483a764b9528ff77f47a2bcf749372a5cbf1bc74a","abstract_canon_sha256":"5d37aad78d599a067400246f3fbce9efe8b932679571f4f76cfb2a37cd2a1a92"},"schema_version":"1.0"},"canonical_sha256":"71f35e4786317e8674a116223763cedbc615cb54559d9ccfdb4bfb39143dcc63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:38.242423Z","signature_b64":"rg5JSbn1CMXQ8lWjNlkUjxEMdKckqjR686kOkDdGAMjvdWvx0+TlgFrQU7pwNqQpuzGGdLQB9V+XR9oqSxOBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71f35e4786317e8674a116223763cedbc615cb54559d9ccfdb4bfb39143dcc63","last_reissued_at":"2026-07-05T03:54:38.241801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:38.241801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.03371","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":"2026-07-05T03:54:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i9kx7LjOQHSbwWgid7nzP3UY/0bWwmDT4US5U9h/Bm65VD1onWcPAE+2ydk9WE17CkagYR907IjBWJazIKgvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:23:09.078339Z"},"content_sha256":"8c1d1117af9dabdaa2733c4de4fbc393703bf5b188b17f59e4777dd377ca6fcb","schema_version":"1.0","event_id":"sha256:8c1d1117af9dabdaa2733c4de4fbc393703bf5b188b17f59e4777dd377ca6fcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OHZV4R4GGF7IM5FBCYRDOY6O3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cedille: A large autoregressive French language model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Florian Laurent, Martin M\\\"uller","submitted_at":"2022-02-07T17:40:43Z","abstract_excerpt":"Scaling up the size and training of autoregressive language models has enabled novel ways of solving Natural Language Processing tasks using zero-shot and few-shot learning. While extreme-scale language models such as GPT-3 offer multilingual capabilities, zero-shot learning for languages other than English remain largely unexplored. Here, we introduce Cedille, a large open source auto-regressive language model, specifically trained for the French language. Our results show that Cedille outperforms existing French language models and is competitive with GPT-3 on a range of French zero-shot ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03371","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/2202.03371/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":"2026-07-05T03:54:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ia3NQQJ7X5DsC4YvEJaYCKV9x331vuoh+qjZcrCNYw8+gTPOSb0SYgxqj6m7i/9OixcL+eTN3r2zLpGApgcaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:23:09.079242Z"},"content_sha256":"0a23c4c36e3e8f1622fd6a1b287e4c30fd74b1806599800edb85539d1e5f348b","schema_version":"1.0","event_id":"sha256:0a23c4c36e3e8f1622fd6a1b287e4c30fd74b1806599800edb85539d1e5f348b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHZV4R4GGF7IM5FBCYRDOY6O3P/bundle.json","state_url":"https://pith.science/pith/OHZV4R4GGF7IM5FBCYRDOY6O3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHZV4R4GGF7IM5FBCYRDOY6O3P/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":"2026-08-05T13:23:09Z","links":{"resolver":"https://pith.science/pith/OHZV4R4GGF7IM5FBCYRDOY6O3P","bundle":"https://pith.science/pith/OHZV4R4GGF7IM5FBCYRDOY6O3P/bundle.json","state":"https://pith.science/pith/OHZV4R4GGF7IM5FBCYRDOY6O3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHZV4R4GGF7IM5FBCYRDOY6O3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OHZV4R4GGF7IM5FBCYRDOY6O3P","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":"5d37aad78d599a067400246f3fbce9efe8b932679571f4f76cfb2a37cd2a1a92","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-07T17:40:43Z","title_canon_sha256":"655f49714970a3adda6215c483a764b9528ff77f47a2bcf749372a5cbf1bc74a"},"schema_version":"1.0","source":{"id":"2202.03371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03371","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03371v1","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03371","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"OHZV4R4GGF7I","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"OHZV4R4GGF7IM5FB","created_at":"2026-07-05T03:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"OHZV4R4G","created_at":"2026-07-05T03:54:38Z"}],"graph_snapshots":[{"event_id":"sha256:0a23c4c36e3e8f1622fd6a1b287e4c30fd74b1806599800edb85539d1e5f348b","target":"graph","created_at":"2026-07-05T03:54:38Z","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/2202.03371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling up the size and training of autoregressive language models has enabled novel ways of solving Natural Language Processing tasks using zero-shot and few-shot learning. While extreme-scale language models such as GPT-3 offer multilingual capabilities, zero-shot learning for languages other than English remain largely unexplored. Here, we introduce Cedille, a large open source auto-regressive language model, specifically trained for the French language. Our results show that Cedille outperforms existing French language models and is competitive with GPT-3 on a range of French zero-shot ben","authors_text":"Florian Laurent, Martin M\\\"uller","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-07T17:40:43Z","title":"Cedille: A large autoregressive French language model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03371","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":"sha256:8c1d1117af9dabdaa2733c4de4fbc393703bf5b188b17f59e4777dd377ca6fcb","target":"record","created_at":"2026-07-05T03:54:38Z","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":"5d37aad78d599a067400246f3fbce9efe8b932679571f4f76cfb2a37cd2a1a92","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-07T17:40:43Z","title_canon_sha256":"655f49714970a3adda6215c483a764b9528ff77f47a2bcf749372a5cbf1bc74a"},"schema_version":"1.0","source":{"id":"2202.03371","kind":"arxiv","version":1}},"canonical_sha256":"71f35e4786317e8674a116223763cedbc615cb54559d9ccfdb4bfb39143dcc63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71f35e4786317e8674a116223763cedbc615cb54559d9ccfdb4bfb39143dcc63","first_computed_at":"2026-07-05T03:54:38.241801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:38.241801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rg5JSbn1CMXQ8lWjNlkUjxEMdKckqjR686kOkDdGAMjvdWvx0+TlgFrQU7pwNqQpuzGGdLQB9V+XR9oqSxOBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:38.242423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c1d1117af9dabdaa2733c4de4fbc393703bf5b188b17f59e4777dd377ca6fcb","sha256:0a23c4c36e3e8f1622fd6a1b287e4c30fd74b1806599800edb85539d1e5f348b"],"state_sha256":"b1ab45d0f19532d32ad72bdaae324b5cd3667493d7fb00d4189bf196dde866f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0AmUE552ZukR0gWqb/x8AAV/xc6B6XAMMn2awvFstbgaFXG/az9Ev8a8NCQlnnvNeAlYXXDtm2szAAAMao0GDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:23:09.089357Z","bundle_sha256":"cb205ca4fff0bcd616215735927889eed6b69c772b240c1f951e72b1be43f49e"}}