{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z43OLC2J5MN6XOBKIXTN65QARJ","short_pith_number":"pith:Z43OLC2J","canonical_record":{"source":{"id":"2405.20468","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T20:34:37Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"ce8ecb967ca417f101cdf495ae8d2e3b9c53f1e45bd1076bee05becddb67e27d","abstract_canon_sha256":"232027693da3e3c7af1f8348d323e8d280d0e080b804c9b65f23e810b45fbc08"},"schema_version":"1.0"},"canonical_sha256":"cf36e58b49eb1bebb82a45e6df76008a5e6d39b012dbc2d98a3386e88e7a0cf7","source":{"kind":"arxiv","id":"2405.20468","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20468","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20468v2","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20468","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"Z43OLC2J5MN6","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"Z43OLC2J5MN6XOBK","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"Z43OLC2J","created_at":"2026-07-05T08:32:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z43OLC2J5MN6XOBKIXTN65QARJ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20468","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T20:34:37Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"ce8ecb967ca417f101cdf495ae8d2e3b9c53f1e45bd1076bee05becddb67e27d","abstract_canon_sha256":"232027693da3e3c7af1f8348d323e8d280d0e080b804c9b65f23e810b45fbc08"},"schema_version":"1.0"},"canonical_sha256":"cf36e58b49eb1bebb82a45e6df76008a5e6d39b012dbc2d98a3386e88e7a0cf7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:41.480033Z","signature_b64":"nweK8PLmusxau+g1vOnu3HMDicVO6uXR/UsnpPXSLDMHbEqgk+KkfApcVcc+INKZ6csmE/cr2yctzvnszHngCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf36e58b49eb1bebb82a45e6df76008a5e6d39b012dbc2d98a3386e88e7a0cf7","last_reissued_at":"2026-07-05T08:32:41.479547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:41.479547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20468","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":"2026-07-05T08:32:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YrA0HVEJt+q+ZNpMbeYUP+8M11Piw8VfAxptLJIfhoXoCJYr6gKQBd66ZWwH2DlvRgBx2MOlBminflm4BUF+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:00:01.923509Z"},"content_sha256":"ab8e0d8646427096189ffa1f6170e8363c82a6d907e2b6bb8ce47fe18ecaed54","schema_version":"1.0","event_id":"sha256:ab8e0d8646427096189ffa1f6170e8363c82a6d907e2b6bb8ce47fe18ecaed54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z43OLC2J5MN6XOBKIXTN65QARJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MTEB-French: Resources for French Sentence Embedding Evaluation and Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Imene Kerboua, Marion Schaeffer, Mathieu Ciancone, Wissam Siblini","submitted_at":"2024-05-30T20:34:37Z","abstract_excerpt":"Recently, numerous embedding models have been made available and widely used for various NLP tasks. The Massive Text Embedding Benchmark (MTEB) has primarily simplified the process of choosing a model that performs well for several tasks in English, but extensions to other languages remain challenging. This is why we expand MTEB to propose the first massive benchmark of sentence embeddings for French. We gather 15 existing datasets in an easy-to-use interface and create three new French datasets for a global evaluation of 8 task categories. We compare 51 carefully selected embedding models on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20468","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/2405.20468/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":"2026-07-05T08:32:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xd53GJzXKvx84YUogb1nMyERmeAZfUeERWEM2jwRgBMP/WpsRtkzD+hzhkcbg6K48dUPZgL0Yp+dOODzHMrPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:00:01.924301Z"},"content_sha256":"2d5f65e65d8046bcf3d038e7508039cdf66b65923f827d27b44080f8a3e0cb86","schema_version":"1.0","event_id":"sha256:2d5f65e65d8046bcf3d038e7508039cdf66b65923f827d27b44080f8a3e0cb86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z43OLC2J5MN6XOBKIXTN65QARJ/bundle.json","state_url":"https://pith.science/pith/Z43OLC2J5MN6XOBKIXTN65QARJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z43OLC2J5MN6XOBKIXTN65QARJ/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":"2026-08-08T07:00:01Z","links":{"resolver":"https://pith.science/pith/Z43OLC2J5MN6XOBKIXTN65QARJ","bundle":"https://pith.science/pith/Z43OLC2J5MN6XOBKIXTN65QARJ/bundle.json","state":"https://pith.science/pith/Z43OLC2J5MN6XOBKIXTN65QARJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z43OLC2J5MN6XOBKIXTN65QARJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z43OLC2J5MN6XOBKIXTN65QARJ","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":"232027693da3e3c7af1f8348d323e8d280d0e080b804c9b65f23e810b45fbc08","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T20:34:37Z","title_canon_sha256":"ce8ecb967ca417f101cdf495ae8d2e3b9c53f1e45bd1076bee05becddb67e27d"},"schema_version":"1.0","source":{"id":"2405.20468","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20468","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20468v2","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20468","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"Z43OLC2J5MN6","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"Z43OLC2J5MN6XOBK","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"Z43OLC2J","created_at":"2026-07-05T08:32:41Z"}],"graph_snapshots":[{"event_id":"sha256:2d5f65e65d8046bcf3d038e7508039cdf66b65923f827d27b44080f8a3e0cb86","target":"graph","created_at":"2026-07-05T08:32:41Z","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/2405.20468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, numerous embedding models have been made available and widely used for various NLP tasks. The Massive Text Embedding Benchmark (MTEB) has primarily simplified the process of choosing a model that performs well for several tasks in English, but extensions to other languages remain challenging. This is why we expand MTEB to propose the first massive benchmark of sentence embeddings for French. We gather 15 existing datasets in an easy-to-use interface and create three new French datasets for a global evaluation of 8 task categories. We compare 51 carefully selected embedding models on ","authors_text":"Imene Kerboua, Marion Schaeffer, Mathieu Ciancone, Wissam Siblini","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T20:34:37Z","title":"MTEB-French: Resources for French Sentence Embedding Evaluation and Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20468","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:ab8e0d8646427096189ffa1f6170e8363c82a6d907e2b6bb8ce47fe18ecaed54","target":"record","created_at":"2026-07-05T08:32:41Z","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":"232027693da3e3c7af1f8348d323e8d280d0e080b804c9b65f23e810b45fbc08","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T20:34:37Z","title_canon_sha256":"ce8ecb967ca417f101cdf495ae8d2e3b9c53f1e45bd1076bee05becddb67e27d"},"schema_version":"1.0","source":{"id":"2405.20468","kind":"arxiv","version":2}},"canonical_sha256":"cf36e58b49eb1bebb82a45e6df76008a5e6d39b012dbc2d98a3386e88e7a0cf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf36e58b49eb1bebb82a45e6df76008a5e6d39b012dbc2d98a3386e88e7a0cf7","first_computed_at":"2026-07-05T08:32:41.479547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:41.479547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nweK8PLmusxau+g1vOnu3HMDicVO6uXR/UsnpPXSLDMHbEqgk+KkfApcVcc+INKZ6csmE/cr2yctzvnszHngCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:41.480033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20468","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab8e0d8646427096189ffa1f6170e8363c82a6d907e2b6bb8ce47fe18ecaed54","sha256:2d5f65e65d8046bcf3d038e7508039cdf66b65923f827d27b44080f8a3e0cb86"],"state_sha256":"8c3b48f9d7e23f0d35a3a3b54b8cf3ee60053fda973a92d7446119fc2112b60d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XQI5qvl2e7Fya5crBJBkQ4b4DjLJwxERP5Bp29doxC2vhRvTYbO+OSkfj6ngU4g9mJBR8LyAWPQV8oFpLALDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:00:01.929438Z","bundle_sha256":"5d97feb0190de1839d37b7e2c84b172c701c00d3b8fe4b14f86d053e05d81f80"}}