{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NSYZUXLKXBTFKRKICUNRZNOBM6","short_pith_number":"pith:NSYZUXLK","canonical_record":{"source":{"id":"2106.06937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-13T07:14:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4dcb7dd4ff9ab67bbf104660fec1381fd4164ebc10085b4cdc45535dc931387","abstract_canon_sha256":"e8f087eb8d0ab8ed5b5264dbef442af3f2517451a1121408df38c479827e0174"},"schema_version":"1.0"},"canonical_sha256":"6cb19a5d6ab866554548151b1cb5c167b671bd497c68793241eb8ffa4f98ecc1","source":{"kind":"arxiv","id":"2106.06937","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06937","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06937v1","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06937","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"NSYZUXLKXBTF","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_16","alias_value":"NSYZUXLKXBTFKRKI","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_8","alias_value":"NSYZUXLK","created_at":"2026-07-05T02:48:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NSYZUXLKXBTFKRKICUNRZNOBM6","target":"record","payload":{"canonical_record":{"source":{"id":"2106.06937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-13T07:14:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4dcb7dd4ff9ab67bbf104660fec1381fd4164ebc10085b4cdc45535dc931387","abstract_canon_sha256":"e8f087eb8d0ab8ed5b5264dbef442af3f2517451a1121408df38c479827e0174"},"schema_version":"1.0"},"canonical_sha256":"6cb19a5d6ab866554548151b1cb5c167b671bd497c68793241eb8ffa4f98ecc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:42.693847Z","signature_b64":"n3GdOGC/OYruiplZxi/32PpAv9TqamGZ8Tqdlqn/RgmiiA+MY9xOGieVjmxagitVFanjKslSBQdhnYbLCQ7QAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cb19a5d6ab866554548151b1cb5c167b671bd497c68793241eb8ffa4f98ecc1","last_reissued_at":"2026-07-05T02:48:42.693452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:42.693452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.06937","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":"2026-07-05T02:48:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QJhgZLTTQ/zSUqWuISTK05qp/npZpOtoL9aryEN9QhpCOZMwCk4ExVoQMTyIcAC8M56BAt1cthPVrtcDqmQtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:44:55.578268Z"},"content_sha256":"7d7879e4d22aa489b3f788c6d1b173b7f06f4dda935f9a7b94a1beddf28c1fba","schema_version":"1.0","event_id":"sha256:7d7879e4d22aa489b3f788c6d1b173b7f06f4dda935f9a7b94a1beddf28c1fba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NSYZUXLKXBTFKRKICUNRZNOBM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bill Yuchen Lin, Seyeon Lee, Xiang Ren, Xiaoyang Qiao","submitted_at":"2021-06-13T07:14:03Z","abstract_excerpt":"Commonsense reasoning research has so far been limited to English. We aim to evaluate and improve popular multilingual language models (ML-LMs) to help advance commonsense reasoning (CSR) beyond English. We collect the Mickey Corpus, consisting of 561k sentences in 11 different languages, which can be used for analyzing and improving ML-LMs. We propose Mickey Probe, a language-agnostic probing task for fairly evaluating the common sense of popular ML-LMs across different languages. In addition, we also create two new datasets, X-CSQA and X-CODAH, by translating their English versions to 15 oth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06937","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/2106.06937/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":"2026-07-05T02:48:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d0picPrJu2B6rXLPrDEJw26E9R9jPg8Ec3U4mVVDqjaTx6p8agLEbLNhchxcpur+jy7TW250HxpbcalzzslxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:44:55.579248Z"},"content_sha256":"a4afe98384bb7c8d260150cd434759113331e1efa27230c740f3f98cb26d974d","schema_version":"1.0","event_id":"sha256:a4afe98384bb7c8d260150cd434759113331e1efa27230c740f3f98cb26d974d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NSYZUXLKXBTFKRKICUNRZNOBM6/bundle.json","state_url":"https://pith.science/pith/NSYZUXLKXBTFKRKICUNRZNOBM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NSYZUXLKXBTFKRKICUNRZNOBM6/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":"2026-08-03T16:44:55Z","links":{"resolver":"https://pith.science/pith/NSYZUXLKXBTFKRKICUNRZNOBM6","bundle":"https://pith.science/pith/NSYZUXLKXBTFKRKICUNRZNOBM6/bundle.json","state":"https://pith.science/pith/NSYZUXLKXBTFKRKICUNRZNOBM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NSYZUXLKXBTFKRKICUNRZNOBM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NSYZUXLKXBTFKRKICUNRZNOBM6","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":"e8f087eb8d0ab8ed5b5264dbef442af3f2517451a1121408df38c479827e0174","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-13T07:14:03Z","title_canon_sha256":"d4dcb7dd4ff9ab67bbf104660fec1381fd4164ebc10085b4cdc45535dc931387"},"schema_version":"1.0","source":{"id":"2106.06937","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06937","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06937v1","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06937","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"NSYZUXLKXBTF","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_16","alias_value":"NSYZUXLKXBTFKRKI","created_at":"2026-07-05T02:48:42Z"},{"alias_kind":"pith_short_8","alias_value":"NSYZUXLK","created_at":"2026-07-05T02:48:42Z"}],"graph_snapshots":[{"event_id":"sha256:a4afe98384bb7c8d260150cd434759113331e1efa27230c740f3f98cb26d974d","target":"graph","created_at":"2026-07-05T02:48:42Z","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/2106.06937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Commonsense reasoning research has so far been limited to English. We aim to evaluate and improve popular multilingual language models (ML-LMs) to help advance commonsense reasoning (CSR) beyond English. We collect the Mickey Corpus, consisting of 561k sentences in 11 different languages, which can be used for analyzing and improving ML-LMs. We propose Mickey Probe, a language-agnostic probing task for fairly evaluating the common sense of popular ML-LMs across different languages. In addition, we also create two new datasets, X-CSQA and X-CODAH, by translating their English versions to 15 oth","authors_text":"Bill Yuchen Lin, Seyeon Lee, Xiang Ren, Xiaoyang Qiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-13T07:14:03Z","title":"Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06937","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":"sha256:7d7879e4d22aa489b3f788c6d1b173b7f06f4dda935f9a7b94a1beddf28c1fba","target":"record","created_at":"2026-07-05T02:48:42Z","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":"e8f087eb8d0ab8ed5b5264dbef442af3f2517451a1121408df38c479827e0174","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-13T07:14:03Z","title_canon_sha256":"d4dcb7dd4ff9ab67bbf104660fec1381fd4164ebc10085b4cdc45535dc931387"},"schema_version":"1.0","source":{"id":"2106.06937","kind":"arxiv","version":1}},"canonical_sha256":"6cb19a5d6ab866554548151b1cb5c167b671bd497c68793241eb8ffa4f98ecc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cb19a5d6ab866554548151b1cb5c167b671bd497c68793241eb8ffa4f98ecc1","first_computed_at":"2026-07-05T02:48:42.693452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:42.693452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n3GdOGC/OYruiplZxi/32PpAv9TqamGZ8Tqdlqn/RgmiiA+MY9xOGieVjmxagitVFanjKslSBQdhnYbLCQ7QAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:42.693847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06937","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d7879e4d22aa489b3f788c6d1b173b7f06f4dda935f9a7b94a1beddf28c1fba","sha256:a4afe98384bb7c8d260150cd434759113331e1efa27230c740f3f98cb26d974d"],"state_sha256":"d742c2277b319e1dc66ba997c27bb1277191e2845db6c4227c82a16fd49bbab0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cppYYYvV0iT+7aKVSQ8JaA78twIzcLLS5FT+FfhP9SQEBYZINOQjen0cCqg7huY4wCO2iQPg1sIMBPqx0PWgDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:44:55.591563Z","bundle_sha256":"61f936d731c00a588784f2dd1bb7d631d5d4b836db33c4afed271d3a23ad0a09"}}