{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FJKNCLMPTG3JFYUYKP3BVQN6EB","short_pith_number":"pith:FJKNCLMP","canonical_record":{"source":{"id":"2110.10318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:06:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ff3c5a30a4a8b1b55288e94fb51076fef43812bc37b99a926b36205f40948f9","abstract_canon_sha256":"49963e432aebc72c1f795d3e8284789f8938c09368551da07186ac6a397a09ff"},"schema_version":"1.0"},"canonical_sha256":"2a54d12d8f99b692e29853f61ac1be2076d19fc39ed4ac44aa7f47a803dcdb2c","source":{"kind":"arxiv","id":"2110.10318","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10318","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10318v1","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10318","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"FJKNCLMPTG3J","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"FJKNCLMPTG3JFYUY","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"FJKNCLMP","created_at":"2026-07-05T03:24:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FJKNCLMPTG3JFYUYKP3BVQN6EB","target":"record","payload":{"canonical_record":{"source":{"id":"2110.10318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:06:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ff3c5a30a4a8b1b55288e94fb51076fef43812bc37b99a926b36205f40948f9","abstract_canon_sha256":"49963e432aebc72c1f795d3e8284789f8938c09368551da07186ac6a397a09ff"},"schema_version":"1.0"},"canonical_sha256":"2a54d12d8f99b692e29853f61ac1be2076d19fc39ed4ac44aa7f47a803dcdb2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:15.839186Z","signature_b64":"NsuQDbUJ3r2N6wU6hjA0rxpWnXgxqera3xFltUtIyxhvlxnxadl9P82Y4ZxbuSMycR5/JdEeVxk1tEdP7ZcDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a54d12d8f99b692e29853f61ac1be2076d19fc39ed4ac44aa7f47a803dcdb2c","last_reissued_at":"2026-07-05T03:24:15.838827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:15.838827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.10318","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":"2026-07-05T03:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQNpTj9/jj9WFe40wD9e3cxoxcz6Pm0h+wfmB4HmXIFt7wKZWHIuHGQk3p/Ng2cOdMAPypAUzaIhdo30uRbGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:20:39.149651Z"},"content_sha256":"6f6af472bf40edc6f58aaf18b0cee16f7494536d52f687f0f1d85313767b2967","schema_version":"1.0","event_id":"sha256:6f6af472bf40edc6f58aaf18b0cee16f7494536d52f687f0f1d85313767b2967"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FJKNCLMPTG3JFYUYKP3BVQN6EB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Multilingual Language Model Pretraining for Social Media Text via Translation Pair Prediction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aria Haghighi, Shubhanshu Mishra","submitted_at":"2021-10-20T00:06:26Z","abstract_excerpt":"We evaluate a simple approach to improving zero-shot multilingual transfer of mBERT on social media corpus by adding a pretraining task called translation pair prediction (TPP), which predicts whether a pair of cross-lingual texts are a valid translation. Our approach assumes access to translations (exact or approximate) between source-target language pairs, where we fine-tune a model on source language task data and evaluate the model in the target language. In particular, we focus on language pairs where transfer learning is difficult for mBERT: those where source and target languages are di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10318","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/2110.10318/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":"2026-07-05T03:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ojB/ZH3LGaTEsW9kdQWcEz6Bnh/xpaNz7akOPhkfiqQHCxd9pW9nNKfA/3Yw24/xcPyCZDSqxemQw2iXX5maBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:20:39.149991Z"},"content_sha256":"6b2990111f56713656c960cfe9c3f9c6f9879cb0819a99b6e36c68666a2bebe7","schema_version":"1.0","event_id":"sha256:6b2990111f56713656c960cfe9c3f9c6f9879cb0819a99b6e36c68666a2bebe7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJKNCLMPTG3JFYUYKP3BVQN6EB/bundle.json","state_url":"https://pith.science/pith/FJKNCLMPTG3JFYUYKP3BVQN6EB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJKNCLMPTG3JFYUYKP3BVQN6EB/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":"2026-08-22T11:20:39Z","links":{"resolver":"https://pith.science/pith/FJKNCLMPTG3JFYUYKP3BVQN6EB","bundle":"https://pith.science/pith/FJKNCLMPTG3JFYUYKP3BVQN6EB/bundle.json","state":"https://pith.science/pith/FJKNCLMPTG3JFYUYKP3BVQN6EB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJKNCLMPTG3JFYUYKP3BVQN6EB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FJKNCLMPTG3JFYUYKP3BVQN6EB","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":"49963e432aebc72c1f795d3e8284789f8938c09368551da07186ac6a397a09ff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:06:26Z","title_canon_sha256":"7ff3c5a30a4a8b1b55288e94fb51076fef43812bc37b99a926b36205f40948f9"},"schema_version":"1.0","source":{"id":"2110.10318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10318","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10318v1","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10318","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"FJKNCLMPTG3J","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"FJKNCLMPTG3JFYUY","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"FJKNCLMP","created_at":"2026-07-05T03:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:6b2990111f56713656c960cfe9c3f9c6f9879cb0819a99b6e36c68666a2bebe7","target":"graph","created_at":"2026-07-05T03:24:15Z","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/2110.10318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate a simple approach to improving zero-shot multilingual transfer of mBERT on social media corpus by adding a pretraining task called translation pair prediction (TPP), which predicts whether a pair of cross-lingual texts are a valid translation. Our approach assumes access to translations (exact or approximate) between source-target language pairs, where we fine-tune a model on source language task data and evaluate the model in the target language. In particular, we focus on language pairs where transfer learning is difficult for mBERT: those where source and target languages are di","authors_text":"Aria Haghighi, Shubhanshu Mishra","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:06:26Z","title":"Improved Multilingual Language Model Pretraining for Social Media Text via Translation Pair Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10318","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":"sha256:6f6af472bf40edc6f58aaf18b0cee16f7494536d52f687f0f1d85313767b2967","target":"record","created_at":"2026-07-05T03:24:15Z","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":"49963e432aebc72c1f795d3e8284789f8938c09368551da07186ac6a397a09ff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:06:26Z","title_canon_sha256":"7ff3c5a30a4a8b1b55288e94fb51076fef43812bc37b99a926b36205f40948f9"},"schema_version":"1.0","source":{"id":"2110.10318","kind":"arxiv","version":1}},"canonical_sha256":"2a54d12d8f99b692e29853f61ac1be2076d19fc39ed4ac44aa7f47a803dcdb2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a54d12d8f99b692e29853f61ac1be2076d19fc39ed4ac44aa7f47a803dcdb2c","first_computed_at":"2026-07-05T03:24:15.838827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:15.838827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NsuQDbUJ3r2N6wU6hjA0rxpWnXgxqera3xFltUtIyxhvlxnxadl9P82Y4ZxbuSMycR5/JdEeVxk1tEdP7ZcDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:15.839186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f6af472bf40edc6f58aaf18b0cee16f7494536d52f687f0f1d85313767b2967","sha256:6b2990111f56713656c960cfe9c3f9c6f9879cb0819a99b6e36c68666a2bebe7"],"state_sha256":"286bcf3508f258fa5c4aa72b8781779910c4d5a4ac7059c2d183dc76d60c2d97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cxVStytgPlU+af34oURLXClQEa3NWbL4wVfAKScM8f3hE2pE/6lrEnMkDh11lM9JU8/+mTCl7dlr7jBBRtdnBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T11:20:39.153502Z","bundle_sha256":"195a89217d192fe5ee1d2670f657e0a9fe4ba9131aace010f79b918debe2c171"}}