{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FGBB4GZXSGITIVOK62RUVBETDJ","short_pith_number":"pith:FGBB4GZX","canonical_record":{"source":{"id":"2007.07834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T16:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"581e5e7a322fb35cd4c18bd405040c54a91f31d6829b27de523c1c31806e9ea9","abstract_canon_sha256":"9a5f967ef9b5085d2fadc040f286a9641498b1c041b78471a7d34ea750536884"},"schema_version":"1.0"},"canonical_sha256":"29821e1b3791913455caf6a34a84931a54a9fe778e9ff78e64a0a71be6de2382","source":{"kind":"arxiv","id":"2007.07834","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.07834","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"2007.07834v2","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07834","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"FGBB4GZXSGIT","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"pith_short_16","alias_value":"FGBB4GZXSGITIVOK","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"pith_short_8","alias_value":"FGBB4GZX","created_at":"2026-07-05T02:29:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FGBB4GZXSGITIVOK62RUVBETDJ","target":"record","payload":{"canonical_record":{"source":{"id":"2007.07834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T16:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"581e5e7a322fb35cd4c18bd405040c54a91f31d6829b27de523c1c31806e9ea9","abstract_canon_sha256":"9a5f967ef9b5085d2fadc040f286a9641498b1c041b78471a7d34ea750536884"},"schema_version":"1.0"},"canonical_sha256":"29821e1b3791913455caf6a34a84931a54a9fe778e9ff78e64a0a71be6de2382","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:54.265377Z","signature_b64":"EfCgosmMFGDgzPeNEgjhTO+qteqgbLDmiyCFcvasIzAYxwSOdb3MvlqkoNCKKqLP1KlhMFO19nIY5KVbQIZKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29821e1b3791913455caf6a34a84931a54a9fe778e9ff78e64a0a71be6de2382","last_reissued_at":"2026-07-05T02:29:54.264682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:54.264682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.07834","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":"2026-07-05T02:29:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9EPwgWBM34m31w+69kz18i9UQiu3WcQBnmvJ2J40n0tomyG1z7Yipjw2McfMp5Y/Oas13iL7v/GRaqPy3gfBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:40:40.494609Z"},"content_sha256":"80d26c55b1a2d4cb743b15d50c56ae22f5944f57d77db5d0afb859de1088964f","schema_version":"1.0","event_id":"sha256:80d26c55b1a2d4cb743b15d50c56ae22f5944f57d77db5d0afb859de1088964f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FGBB4GZXSGITIVOK62RUVBETDJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Heyan Huang, Li Dong, Ming Zhou, Nan Yang, Saksham Singhal, Wenhui Wang, Xian-Ling Mao, Xia Song, Zewen Chi","submitted_at":"2020-07-15T16:58:01Z","abstract_excerpt":"In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better understand the existing methods for learning cross-lingual representations. More importantly, inspired by the framework, we propose a new pre-training task based on contrastive learning. Specifically, we regard a bilingual sentence pair as two views of the same meaning and encourage their encoded representations to be more similar than the negative examples. By lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07834","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/2007.07834/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":"2026-07-05T02:29:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3hYvxhQY+wMuoZrlvXmRXvRAt7kdxxrToGnDCT6+OOJN3eR7YI9tMWEvE64UoiRFgQZepKeZvm2Br1sewsQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:40:40.495127Z"},"content_sha256":"078896b7de897ee1f44964f2ca90b35ec238ad331e2878805f51aa2cba6b5aa8","schema_version":"1.0","event_id":"sha256:078896b7de897ee1f44964f2ca90b35ec238ad331e2878805f51aa2cba6b5aa8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGBB4GZXSGITIVOK62RUVBETDJ/bundle.json","state_url":"https://pith.science/pith/FGBB4GZXSGITIVOK62RUVBETDJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGBB4GZXSGITIVOK62RUVBETDJ/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":"2026-08-17T14:40:40Z","links":{"resolver":"https://pith.science/pith/FGBB4GZXSGITIVOK62RUVBETDJ","bundle":"https://pith.science/pith/FGBB4GZXSGITIVOK62RUVBETDJ/bundle.json","state":"https://pith.science/pith/FGBB4GZXSGITIVOK62RUVBETDJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGBB4GZXSGITIVOK62RUVBETDJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FGBB4GZXSGITIVOK62RUVBETDJ","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":"9a5f967ef9b5085d2fadc040f286a9641498b1c041b78471a7d34ea750536884","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T16:58:01Z","title_canon_sha256":"581e5e7a322fb35cd4c18bd405040c54a91f31d6829b27de523c1c31806e9ea9"},"schema_version":"1.0","source":{"id":"2007.07834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.07834","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"2007.07834v2","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07834","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"FGBB4GZXSGIT","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"pith_short_16","alias_value":"FGBB4GZXSGITIVOK","created_at":"2026-07-05T02:29:54Z"},{"alias_kind":"pith_short_8","alias_value":"FGBB4GZX","created_at":"2026-07-05T02:29:54Z"}],"graph_snapshots":[{"event_id":"sha256:078896b7de897ee1f44964f2ca90b35ec238ad331e2878805f51aa2cba6b5aa8","target":"graph","created_at":"2026-07-05T02:29:54Z","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/2007.07834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better understand the existing methods for learning cross-lingual representations. More importantly, inspired by the framework, we propose a new pre-training task based on contrastive learning. Specifically, we regard a bilingual sentence pair as two views of the same meaning and encourage their encoded representations to be more similar than the negative examples. By lev","authors_text":"Furu Wei, Heyan Huang, Li Dong, Ming Zhou, Nan Yang, Saksham Singhal, Wenhui Wang, Xian-Ling Mao, Xia Song, Zewen Chi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T16:58:01Z","title":"InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07834","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":"sha256:80d26c55b1a2d4cb743b15d50c56ae22f5944f57d77db5d0afb859de1088964f","target":"record","created_at":"2026-07-05T02:29:54Z","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":"9a5f967ef9b5085d2fadc040f286a9641498b1c041b78471a7d34ea750536884","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T16:58:01Z","title_canon_sha256":"581e5e7a322fb35cd4c18bd405040c54a91f31d6829b27de523c1c31806e9ea9"},"schema_version":"1.0","source":{"id":"2007.07834","kind":"arxiv","version":2}},"canonical_sha256":"29821e1b3791913455caf6a34a84931a54a9fe778e9ff78e64a0a71be6de2382","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29821e1b3791913455caf6a34a84931a54a9fe778e9ff78e64a0a71be6de2382","first_computed_at":"2026-07-05T02:29:54.264682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:54.264682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EfCgosmMFGDgzPeNEgjhTO+qteqgbLDmiyCFcvasIzAYxwSOdb3MvlqkoNCKKqLP1KlhMFO19nIY5KVbQIZKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:54.265377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.07834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80d26c55b1a2d4cb743b15d50c56ae22f5944f57d77db5d0afb859de1088964f","sha256:078896b7de897ee1f44964f2ca90b35ec238ad331e2878805f51aa2cba6b5aa8"],"state_sha256":"263a06b2bc10b1fe765916bdcfd5e0470c11cf6ebc654b7a6bade10f47e4bcc4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"geg0uSctu895tXNMrqxG60JBm4soQkXvPP4FwOW0+4gdIlPqrDgFia+4b4ivsiz0UM3jwinvo31pARfbIHxPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:40:40.499839Z","bundle_sha256":"01a3ad316b15e4270d2894af506a379e0fc6274b8f976f5aa4242f9d58844a04"}}