{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NUXNF7F3Z6JWPACQUBPLTUPOZ5","short_pith_number":"pith:NUXNF7F3","canonical_record":{"source":{"id":"2205.06356","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T20:42:48Z","cross_cats_sorted":[],"title_canon_sha256":"c605b546d2f990b2fe2d883b6980f2c0b4ad2a22dd69af0cab79a687dd7bf683","abstract_canon_sha256":"b2730912d5ed2a970f26e8008c954957e6d91f3747fa9df49ed573e7631ca957"},"schema_version":"1.0"},"canonical_sha256":"6d2ed2fcbbcf93678050a05eb9d1eecf4b4b34ebe2b788ea351c934960039b79","source":{"kind":"arxiv","id":"2205.06356","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.06356","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2205.06356v2","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06356","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"NUXNF7F3Z6JW","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"NUXNF7F3Z6JWPACQ","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"NUXNF7F3","created_at":"2026-07-05T05:15:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NUXNF7F3Z6JWPACQUBPLTUPOZ5","target":"record","payload":{"canonical_record":{"source":{"id":"2205.06356","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T20:42:48Z","cross_cats_sorted":[],"title_canon_sha256":"c605b546d2f990b2fe2d883b6980f2c0b4ad2a22dd69af0cab79a687dd7bf683","abstract_canon_sha256":"b2730912d5ed2a970f26e8008c954957e6d91f3747fa9df49ed573e7631ca957"},"schema_version":"1.0"},"canonical_sha256":"6d2ed2fcbbcf93678050a05eb9d1eecf4b4b34ebe2b788ea351c934960039b79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:39.618552Z","signature_b64":"AAlAbx2ITJm7i38k299qWkGXg2EB3kQtIKX5FnyPxzjAWvCUspDfwD1thQBmXn2iKztjCSsOD2G13Ips6AszAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d2ed2fcbbcf93678050a05eb9d1eecf4b4b34ebe2b788ea351c934960039b79","last_reissued_at":"2026-07-05T05:15:39.618091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:39.618091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.06356","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":"2026-07-05T05:15:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHrdwusuwGfvmV64wLbDOrSyFEGPmcbhGWbyaH6R35ZOwoeCYrJKXvHf0XqYVWsqQDwcvhvKT/oTtaz88VE7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:08:09.835225Z"},"content_sha256":"c91611b0e0ad5f063ebf8f19372baac1494e59a3169acc741b7ee036b7e9b1a6","schema_version":"1.0","event_id":"sha256:c91611b0e0ad5f063ebf8f19372baac1494e59a3169acc741b7ee036b7e9b1a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NUXNF7F3Z6JWPACQUBPLTUPOZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kabir Ahuja, Monojit Choudhury, Sandipan Dandapat, Sunayana Sitaram","submitted_at":"2022-05-12T20:42:48Z","abstract_excerpt":"Although recent Massively Multilingual Language Models (MMLMs) like mBERT and XLMR support around 100 languages, most existing multilingual NLP benchmarks provide evaluation data in only a handful of these languages with little linguistic diversity. We argue that this makes the existing practices in multilingual evaluation unreliable and does not provide a full picture of the performance of MMLMs across the linguistic landscape. We propose that the recent work done in Performance Prediction for NLP tasks can serve as a potential solution in fixing benchmarking in Multilingual NLP by utilizing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06356","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/2205.06356/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":"2026-07-05T05:15:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XK3QN+Kx5O8KUehzlgtFxlb58teHllDiCiD74W/oqN/649VQ1JzPkDrTkXuF6hsGGC/2c3MKuD9MNHz72UkIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:08:09.836175Z"},"content_sha256":"bc9c411e43f64511301d94209e92d2b7c8ec507b96ea9e301a5a77c0cc900528","schema_version":"1.0","event_id":"sha256:bc9c411e43f64511301d94209e92d2b7c8ec507b96ea9e301a5a77c0cc900528"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NUXNF7F3Z6JWPACQUBPLTUPOZ5/bundle.json","state_url":"https://pith.science/pith/NUXNF7F3Z6JWPACQUBPLTUPOZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NUXNF7F3Z6JWPACQUBPLTUPOZ5/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":"2026-08-09T23:08:09Z","links":{"resolver":"https://pith.science/pith/NUXNF7F3Z6JWPACQUBPLTUPOZ5","bundle":"https://pith.science/pith/NUXNF7F3Z6JWPACQUBPLTUPOZ5/bundle.json","state":"https://pith.science/pith/NUXNF7F3Z6JWPACQUBPLTUPOZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NUXNF7F3Z6JWPACQUBPLTUPOZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NUXNF7F3Z6JWPACQUBPLTUPOZ5","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":"b2730912d5ed2a970f26e8008c954957e6d91f3747fa9df49ed573e7631ca957","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T20:42:48Z","title_canon_sha256":"c605b546d2f990b2fe2d883b6980f2c0b4ad2a22dd69af0cab79a687dd7bf683"},"schema_version":"1.0","source":{"id":"2205.06356","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.06356","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2205.06356v2","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06356","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"NUXNF7F3Z6JW","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"NUXNF7F3Z6JWPACQ","created_at":"2026-07-05T05:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"NUXNF7F3","created_at":"2026-07-05T05:15:39Z"}],"graph_snapshots":[{"event_id":"sha256:bc9c411e43f64511301d94209e92d2b7c8ec507b96ea9e301a5a77c0cc900528","target":"graph","created_at":"2026-07-05T05:15:39Z","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/2205.06356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although recent Massively Multilingual Language Models (MMLMs) like mBERT and XLMR support around 100 languages, most existing multilingual NLP benchmarks provide evaluation data in only a handful of these languages with little linguistic diversity. We argue that this makes the existing practices in multilingual evaluation unreliable and does not provide a full picture of the performance of MMLMs across the linguistic landscape. We propose that the recent work done in Performance Prediction for NLP tasks can serve as a potential solution in fixing benchmarking in Multilingual NLP by utilizing ","authors_text":"Kabir Ahuja, Monojit Choudhury, Sandipan Dandapat, Sunayana Sitaram","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T20:42:48Z","title":"Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06356","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:c91611b0e0ad5f063ebf8f19372baac1494e59a3169acc741b7ee036b7e9b1a6","target":"record","created_at":"2026-07-05T05:15:39Z","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":"b2730912d5ed2a970f26e8008c954957e6d91f3747fa9df49ed573e7631ca957","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-12T20:42:48Z","title_canon_sha256":"c605b546d2f990b2fe2d883b6980f2c0b4ad2a22dd69af0cab79a687dd7bf683"},"schema_version":"1.0","source":{"id":"2205.06356","kind":"arxiv","version":2}},"canonical_sha256":"6d2ed2fcbbcf93678050a05eb9d1eecf4b4b34ebe2b788ea351c934960039b79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d2ed2fcbbcf93678050a05eb9d1eecf4b4b34ebe2b788ea351c934960039b79","first_computed_at":"2026-07-05T05:15:39.618091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:39.618091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AAlAbx2ITJm7i38k299qWkGXg2EB3kQtIKX5FnyPxzjAWvCUspDfwD1thQBmXn2iKztjCSsOD2G13Ips6AszAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:39.618552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.06356","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c91611b0e0ad5f063ebf8f19372baac1494e59a3169acc741b7ee036b7e9b1a6","sha256:bc9c411e43f64511301d94209e92d2b7c8ec507b96ea9e301a5a77c0cc900528"],"state_sha256":"16b862b4c4d85956b883127a5ad014e36dfbc0ae6efc265c481a0a41aff97d4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3S2vvTnNV8kTUFKdL1TWQbVw/UbZ34xIc9mP9fijZkJ6ubwW0cMssL8YcS4aPdmygq5KBfTLjgVL9702Mzr9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:08:09.842729Z","bundle_sha256":"1c07cfd3fe5c46f7c20e34d4054e4fbf2b36e5d2cb17aaf9a93327e6185085c9"}}