{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Z52BXLJPOVYNXCWOMA3GFJLDTO","short_pith_number":"pith:Z52BXLJP","canonical_record":{"source":{"id":"2210.07316","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-13T19:42:08Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c6029532035edb5cd95cc52d76c8c664a42e23bb7c566963351eb1aac851f070","abstract_canon_sha256":"b9f0eef31e7d1249bfde4e27f63923dc5697cd582fa9ac5ce1b60fe9dea003f8"},"schema_version":"1.0"},"canonical_sha256":"cf741bad2f7570db8ace603662a5639bbdb476bcbc363e216b26c2d777f1a6ac","source":{"kind":"arxiv","id":"2210.07316","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07316","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07316v3","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07316","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"Z52BXLJPOVYN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"Z52BXLJPOVYNXCWO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"Z52BXLJP","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Z52BXLJPOVYNXCWOMA3GFJLDTO","target":"record","payload":{"canonical_record":{"source":{"id":"2210.07316","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-13T19:42:08Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c6029532035edb5cd95cc52d76c8c664a42e23bb7c566963351eb1aac851f070","abstract_canon_sha256":"b9f0eef31e7d1249bfde4e27f63923dc5697cd582fa9ac5ce1b60fe9dea003f8"},"schema_version":"1.0"},"canonical_sha256":"cf741bad2f7570db8ace603662a5639bbdb476bcbc363e216b26c2d777f1a6ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.800465Z","signature_b64":"k8355wyFAxIYh25I/ji7qG/Re7KE2M1dTL03wjYGfsj4Crs9MmQpUiFdF9a9vl/SerK6/1TrLxNjD1pTO6pyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf741bad2f7570db8ace603662a5639bbdb476bcbc363e216b26c2d777f1a6ac","last_reissued_at":"2026-05-17T23:38:52.799771Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.799771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.07316","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":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pcfl1cKZXUlDIIaTQ6xEkGnLYiRqmt/k7KwqDQCJA0GzHeXu1Ys91d2y2FqcDMRcpBdRxAjJaSTAgAREte0hDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:47:47.658377Z"},"content_sha256":"4ded2fd3f3a09ebc27e198c9e0b67080c7c43ffd7e6d447fc18dcf4929f1cde1","schema_version":"1.0","event_id":"sha256:4ded2fd3f3a09ebc27e198c9e0b67080c7c43ffd7e6d447fc18dcf4929f1cde1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Z52BXLJPOVYNXCWOMA3GFJLDTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MTEB: Massive Text Embedding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A new benchmark shows no single text embedding method performs best across all tasks.","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lo\\\"ic Magne, Niklas Muennighoff, Nils Reimers, Nouamane Tazi","submitted_at":"2022-10-13T19:42:08Z","abstract_excerpt":"Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be equally well applied to other tasks like clustering or reranking. This makes progress in the field difficult to track, as various models are constantly being proposed without proper evaluation. To solve this problem, we introduce the Massive Text Embedding Benchmark (MTEB). MTEB spans 8 embedding tasks covering a total of 58 datasets and 112 languages. Through t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 8 tasks and 58 datasets chosen are sufficiently representative of the full range of real-world embedding applications so that performance on MTEB predicts usefulness elsewhere.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MTEB is a new multi-task benchmark showing that no single text embedding model leads on all 8 tasks across 58 datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new benchmark shows no single text embedding method performs best across all tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7ab1a36f952b2168275f60602fb2ab1252318161184fa61c3159a31bda5c3ac4"},"source":{"id":"2210.07316","kind":"arxiv","version":3},"verdict":{"id":"26569f9a-67bb-44a6-a5cd-e1af2c709a23","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T10:11:33.391781Z","strongest_claim":"Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks.","one_line_summary":"MTEB is a new multi-task benchmark showing that no single text embedding model leads on all 8 tasks across 58 datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 8 tasks and 58 datasets chosen are sufficiently representative of the full range of real-world embedding applications so that performance on MTEB predicts usefulness elsewhere.","pith_extraction_headline":"A new benchmark shows no single text embedding method performs best across all tasks."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"dd497eacc74514a675723cf8d1755fc838ee4ed8793d9c1c4f117c64022fad16"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"26569f9a-67bb-44a6-a5cd-e1af2c709a23"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/l1TDf/8DQ/FP+eoTEfOmk6RY+1yrbX7ossP/iSVqqBthkpsZtTJTk25uJ52vA1dZACfxV9DHG3eY0DoKxjJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:47:47.658856Z"},"content_sha256":"9c9830ca6bddaaf319cce6f6de7daac8ce0287aaa67d00bed28d84dc675fe729","schema_version":"1.0","event_id":"sha256:9c9830ca6bddaaf319cce6f6de7daac8ce0287aaa67d00bed28d84dc675fe729"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z52BXLJPOVYNXCWOMA3GFJLDTO/bundle.json","state_url":"https://pith.science/pith/Z52BXLJPOVYNXCWOMA3GFJLDTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z52BXLJPOVYNXCWOMA3GFJLDTO/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":"2026-06-02T20:47:47Z","links":{"resolver":"https://pith.science/pith/Z52BXLJPOVYNXCWOMA3GFJLDTO","bundle":"https://pith.science/pith/Z52BXLJPOVYNXCWOMA3GFJLDTO/bundle.json","state":"https://pith.science/pith/Z52BXLJPOVYNXCWOMA3GFJLDTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z52BXLJPOVYNXCWOMA3GFJLDTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z52BXLJPOVYNXCWOMA3GFJLDTO","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":"b9f0eef31e7d1249bfde4e27f63923dc5697cd582fa9ac5ce1b60fe9dea003f8","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-13T19:42:08Z","title_canon_sha256":"c6029532035edb5cd95cc52d76c8c664a42e23bb7c566963351eb1aac851f070"},"schema_version":"1.0","source":{"id":"2210.07316","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07316","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07316v3","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07316","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"Z52BXLJPOVYN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"Z52BXLJPOVYNXCWO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"Z52BXLJP","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:9c9830ca6bddaaf319cce6f6de7daac8ce0287aaa67d00bed28d84dc675fe729","target":"graph","created_at":"2026-05-17T23:38:52Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 8 tasks and 58 datasets chosen are sufficiently representative of the full range of real-world embedding applications so that performance on MTEB predicts usefulness elsewhere."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MTEB is a new multi-task benchmark showing that no single text embedding model leads on all 8 tasks across 58 datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A new benchmark shows no single text embedding method performs best across all tasks."}],"snapshot_sha256":"7ab1a36f952b2168275f60602fb2ab1252318161184fa61c3159a31bda5c3ac4"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"dd497eacc74514a675723cf8d1755fc838ee4ed8793d9c1c4f117c64022fad16"},"paper":{"abstract_excerpt":"Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be equally well applied to other tasks like clustering or reranking. This makes progress in the field difficult to track, as various models are constantly being proposed without proper evaluation. To solve this problem, we introduce the Massive Text Embedding Benchmark (MTEB). MTEB spans 8 embedding tasks covering a total of 58 datasets and 112 languages. Through t","authors_text":"Lo\\\"ic Magne, Niklas Muennighoff, Nils Reimers, Nouamane Tazi","cross_cats":["cs.IR","cs.LG"],"headline":"A new benchmark shows no single text embedding method performs best across all tasks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-13T19:42:08Z","title":"MTEB: Massive Text Embedding Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07316","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T10:11:33.391781Z","id":"26569f9a-67bb-44a6-a5cd-e1af2c709a23","model_set":{"reader":"grok-4.3"},"one_line_summary":"MTEB is a new multi-task benchmark showing that no single text embedding model leads on all 8 tasks across 58 datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A new benchmark shows no single text embedding method performs best across all tasks.","strongest_claim":"Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks.","weakest_assumption":"The 8 tasks and 58 datasets chosen are sufficiently representative of the full range of real-world embedding applications so that performance on MTEB predicts usefulness elsewhere."}},"verdict_id":"26569f9a-67bb-44a6-a5cd-e1af2c709a23"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4ded2fd3f3a09ebc27e198c9e0b67080c7c43ffd7e6d447fc18dcf4929f1cde1","target":"record","created_at":"2026-05-17T23:38:52Z","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":"b9f0eef31e7d1249bfde4e27f63923dc5697cd582fa9ac5ce1b60fe9dea003f8","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-13T19:42:08Z","title_canon_sha256":"c6029532035edb5cd95cc52d76c8c664a42e23bb7c566963351eb1aac851f070"},"schema_version":"1.0","source":{"id":"2210.07316","kind":"arxiv","version":3}},"canonical_sha256":"cf741bad2f7570db8ace603662a5639bbdb476bcbc363e216b26c2d777f1a6ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf741bad2f7570db8ace603662a5639bbdb476bcbc363e216b26c2d777f1a6ac","first_computed_at":"2026-05-17T23:38:52.799771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.799771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k8355wyFAxIYh25I/ji7qG/Re7KE2M1dTL03wjYGfsj4Crs9MmQpUiFdF9a9vl/SerK6/1TrLxNjD1pTO6pyAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.800465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07316","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ded2fd3f3a09ebc27e198c9e0b67080c7c43ffd7e6d447fc18dcf4929f1cde1","sha256:9c9830ca6bddaaf319cce6f6de7daac8ce0287aaa67d00bed28d84dc675fe729"],"state_sha256":"8c6159b31e90354c79dd6a3c61fe2658d67b67e19b0944d000998de8bd4d2b2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnBN04TMrp5D8m2+9sqmsICL/hNp42i1+S0sBPYPjTVkhHcLXCyAxso3tCC5WTvAEONH+R2wBqLfFa6XeefGDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:47:47.661453Z","bundle_sha256":"92c1550c95d14d2f75945676b1380b91d8f6c45fe6f235a0a83363af306fbc04"}}