{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:T63CN2HGVNCV23SZ3ETCQ4O4X5","short_pith_number":"pith:T63CN2HG","canonical_record":{"source":{"id":"1911.03894","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T10:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"4b0a87a860d3ec567e86c55dbeed0e08d4c05634d8a1e127643e45a42fb01741","abstract_canon_sha256":"279158c12dfea0dd68fa1f68c39068ea3df4f8fcb4d3cf71ee0283958f099e3d"},"schema_version":"1.0"},"canonical_sha256":"9fb626e8e6ab455d6e59d9262871dcbf6ebce876e7e0e799f8fc6165c68b1a87","source":{"kind":"arxiv","id":"1911.03894","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03894","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03894v3","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03894","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"T63CN2HGVNCV","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"T63CN2HGVNCV23SZ","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"T63CN2HG","created_at":"2026-07-05T01:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:T63CN2HGVNCV23SZ3ETCQ4O4X5","target":"record","payload":{"canonical_record":{"source":{"id":"1911.03894","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T10:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"4b0a87a860d3ec567e86c55dbeed0e08d4c05634d8a1e127643e45a42fb01741","abstract_canon_sha256":"279158c12dfea0dd68fa1f68c39068ea3df4f8fcb4d3cf71ee0283958f099e3d"},"schema_version":"1.0"},"canonical_sha256":"9fb626e8e6ab455d6e59d9262871dcbf6ebce876e7e0e799f8fc6165c68b1a87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:49.067380Z","signature_b64":"U6GUMqU5YKPXxBm/SJdvVdTfWk4CjSHbrDGhut3EprblMbe6OWG0vTv3pY6WgwSz/EU26fUXyrizhZl+6u4SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fb626e8e6ab455d6e59d9262871dcbf6ebce876e7e0e799f8fc6165c68b1a87","last_reissued_at":"2026-07-05T01:28:49.066883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:49.066883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.03894","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":"2026-07-05T01:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sm4dwYzfYFWX0Y1e4VvYLXsOjQDfMXk2wt/nNB+E0KLroE0YmHAH8WQrGeP7uvwBctQmAhI1cMylXSdR0u3yDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:33:19.765875Z"},"content_sha256":"da02e8497bc119ddca9d03c8dc1b54f6e291d2df0756c3147acbbb5ecc9371b5","schema_version":"1.0","event_id":"sha256:da02e8497bc119ddca9d03c8dc1b54f6e291d2df0756c3147acbbb5ecc9371b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:T63CN2HGVNCV23SZ3ETCQ4O4X5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CamemBERT: a Tasty French Language Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Muller, Beno\\^it Sagot, Djam\\'e Seddah, \\'Eric Villemonte de la Clergerie, Laurent Romary, Louis Martin, Pedro Javier Ortiz Su\\'arez, Yoann Dupont","submitted_at":"2019-11-10T10:46:37Z","abstract_excerpt":"Pretrained language models are now ubiquitous in Natural Language Processing. Despite their success, most available models have either been trained on English data or on the concatenation of data in multiple languages. This makes practical use of such models --in all languages except English-- very limited. In this paper, we investigate the feasibility of training monolingual Transformer-based language models for other languages, taking French as an example and evaluating our language models on part-of-speech tagging, dependency parsing, named entity recognition and natural language inference "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03894","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/1911.03894/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":"2026-07-05T01:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ma9J13UPjDp7FPG0OxXFHCVgp8ZmEV2ozYbHmwr3B/44mGpV8Emxru+ZGBqEERPr3VHMBSa8gT3S1uJuGC7hAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:33:19.766378Z"},"content_sha256":"f99a31811a7167e50ee5f73925f19477e99a417d47c0c5a43973595678a77a39","schema_version":"1.0","event_id":"sha256:f99a31811a7167e50ee5f73925f19477e99a417d47c0c5a43973595678a77a39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T63CN2HGVNCV23SZ3ETCQ4O4X5/bundle.json","state_url":"https://pith.science/pith/T63CN2HGVNCV23SZ3ETCQ4O4X5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T63CN2HGVNCV23SZ3ETCQ4O4X5/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":"2026-08-22T18:33:19Z","links":{"resolver":"https://pith.science/pith/T63CN2HGVNCV23SZ3ETCQ4O4X5","bundle":"https://pith.science/pith/T63CN2HGVNCV23SZ3ETCQ4O4X5/bundle.json","state":"https://pith.science/pith/T63CN2HGVNCV23SZ3ETCQ4O4X5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T63CN2HGVNCV23SZ3ETCQ4O4X5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:T63CN2HGVNCV23SZ3ETCQ4O4X5","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":"279158c12dfea0dd68fa1f68c39068ea3df4f8fcb4d3cf71ee0283958f099e3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T10:46:37Z","title_canon_sha256":"4b0a87a860d3ec567e86c55dbeed0e08d4c05634d8a1e127643e45a42fb01741"},"schema_version":"1.0","source":{"id":"1911.03894","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03894","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03894v3","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03894","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"T63CN2HGVNCV","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"T63CN2HGVNCV23SZ","created_at":"2026-07-05T01:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"T63CN2HG","created_at":"2026-07-05T01:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:f99a31811a7167e50ee5f73925f19477e99a417d47c0c5a43973595678a77a39","target":"graph","created_at":"2026-07-05T01:28:49Z","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/1911.03894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained language models are now ubiquitous in Natural Language Processing. Despite their success, most available models have either been trained on English data or on the concatenation of data in multiple languages. This makes practical use of such models --in all languages except English-- very limited. In this paper, we investigate the feasibility of training monolingual Transformer-based language models for other languages, taking French as an example and evaluating our language models on part-of-speech tagging, dependency parsing, named entity recognition and natural language inference ","authors_text":"Benjamin Muller, Beno\\^it Sagot, Djam\\'e Seddah, \\'Eric Villemonte de la Clergerie, Laurent Romary, Louis Martin, Pedro Javier Ortiz Su\\'arez, Yoann Dupont","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T10:46:37Z","title":"CamemBERT: a Tasty French Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03894","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:da02e8497bc119ddca9d03c8dc1b54f6e291d2df0756c3147acbbb5ecc9371b5","target":"record","created_at":"2026-07-05T01:28:49Z","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":"279158c12dfea0dd68fa1f68c39068ea3df4f8fcb4d3cf71ee0283958f099e3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T10:46:37Z","title_canon_sha256":"4b0a87a860d3ec567e86c55dbeed0e08d4c05634d8a1e127643e45a42fb01741"},"schema_version":"1.0","source":{"id":"1911.03894","kind":"arxiv","version":3}},"canonical_sha256":"9fb626e8e6ab455d6e59d9262871dcbf6ebce876e7e0e799f8fc6165c68b1a87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fb626e8e6ab455d6e59d9262871dcbf6ebce876e7e0e799f8fc6165c68b1a87","first_computed_at":"2026-07-05T01:28:49.066883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:49.066883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U6GUMqU5YKPXxBm/SJdvVdTfWk4CjSHbrDGhut3EprblMbe6OWG0vTv3pY6WgwSz/EU26fUXyrizhZl+6u4SBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:49.067380Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.03894","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da02e8497bc119ddca9d03c8dc1b54f6e291d2df0756c3147acbbb5ecc9371b5","sha256:f99a31811a7167e50ee5f73925f19477e99a417d47c0c5a43973595678a77a39"],"state_sha256":"e1a9ed773f210e5eb8d6d13cbc7317b15d0e80820447a18588b839917e273d6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rMAbqlpM474OIIoQxbdwa4skvW7SgX3DPNxEL/JSWWQ3u1r1G/EllbArYn2v/8W4Q2S5mEe/DrgPEi+nmWrHAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T18:33:19.770186Z","bundle_sha256":"3690094544d0507f769dfdec692ab8302bf6f4311786ee56467b67a150999553"}}