{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6EQ3SFQQONAGEZJANJ5OJSSKYN","short_pith_number":"pith:6EQ3SFQQ","canonical_record":{"source":{"id":"2205.10964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-22T23:58:24Z","cross_cats_sorted":[],"title_canon_sha256":"be83bf7ccda1f39c801fc333bfc32bafa0af6c874f4e8530bcaabf25d1578b97","abstract_canon_sha256":"b997132c0461c00a4aa744540313875745fc5f647698b7a611636108a4c76ad2"},"schema_version":"1.0"},"canonical_sha256":"f121b9161073406265206a7ae4ca4ac368a05a1d1cf42659621153463748c6e3","source":{"kind":"arxiv","id":"2205.10964","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10964","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10964v2","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10964","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"6EQ3SFQQONAG","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"6EQ3SFQQONAGEZJA","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"6EQ3SFQQ","created_at":"2026-07-05T05:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6EQ3SFQQONAGEZJANJ5OJSSKYN","target":"record","payload":{"canonical_record":{"source":{"id":"2205.10964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-22T23:58:24Z","cross_cats_sorted":[],"title_canon_sha256":"be83bf7ccda1f39c801fc333bfc32bafa0af6c874f4e8530bcaabf25d1578b97","abstract_canon_sha256":"b997132c0461c00a4aa744540313875745fc5f647698b7a611636108a4c76ad2"},"schema_version":"1.0"},"canonical_sha256":"f121b9161073406265206a7ae4ca4ac368a05a1d1cf42659621153463748c6e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:18.257248Z","signature_b64":"eXq+Hhq7E9A5/jLYMBD8mT1TRS8qoI4OFMwcChJD1cTkNk68Y7l9UzrPobzHj8ExliM6QBYyUT08vzvtGb4wBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f121b9161073406265206a7ae4ca4ac368a05a1d1cf42659621153463748c6e3","last_reissued_at":"2026-07-05T05:09:18.256911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:18.256911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.10964","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":"2026-07-05T05:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tFjm5EHwIjMEGIt0w0K09Vn4uOGu+zHRogGxhg7BFwCHiIKds0Z6/TdR66q+0mT/I5KKXz4Eb8zK1i/peVQNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:58:11.659125Z"},"content_sha256":"8ad6b8d345f729624fb45cf93a8566b0054368e36783e601d92db8fafdbe148e","schema_version":"1.0","event_id":"sha256:8ad6b8d345f729624fb45cf93a8566b0054368e36783e601d92db8fafdbe148e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6EQ3SFQQONAGEZJANJ5OJSSKYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Geometry of Multilingual Language Model Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin K. Bergen, Tyler A. Chang, Zhuowen Tu","submitted_at":"2022-05-22T23:58:24Z","abstract_excerpt":"We assess how multilingual language models maintain a shared multilingual representation space while still encoding language-sensitive information in each language. Using XLM-R as a case study, we show that languages occupy similar linear subspaces after mean-centering, evaluated based on causal effects on language modeling performance and direct comparisons between subspaces for 88 languages. The subspace means differ along language-sensitive axes that are relatively stable throughout middle layers, and these axes encode information such as token vocabularies. Shifting representations by lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10964","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/2205.10964/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":"2026-07-05T05:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t6nmyEwqjyOwDBuX+zhfjtpOYN4Y3xXBRWqAUXmrHezddMzfz1Y3dxKh+nxdJs70WSjQFgZe1dIpjh63PQRVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:58:11.659647Z"},"content_sha256":"642778b7aadea5d69e4629aa52e5fd2ea103b32acedd8cbfa56b4aacd4ef832d","schema_version":"1.0","event_id":"sha256:642778b7aadea5d69e4629aa52e5fd2ea103b32acedd8cbfa56b4aacd4ef832d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EQ3SFQQONAGEZJANJ5OJSSKYN/bundle.json","state_url":"https://pith.science/pith/6EQ3SFQQONAGEZJANJ5OJSSKYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EQ3SFQQONAGEZJANJ5OJSSKYN/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":"2026-08-08T22:58:11Z","links":{"resolver":"https://pith.science/pith/6EQ3SFQQONAGEZJANJ5OJSSKYN","bundle":"https://pith.science/pith/6EQ3SFQQONAGEZJANJ5OJSSKYN/bundle.json","state":"https://pith.science/pith/6EQ3SFQQONAGEZJANJ5OJSSKYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EQ3SFQQONAGEZJANJ5OJSSKYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6EQ3SFQQONAGEZJANJ5OJSSKYN","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":"b997132c0461c00a4aa744540313875745fc5f647698b7a611636108a4c76ad2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-22T23:58:24Z","title_canon_sha256":"be83bf7ccda1f39c801fc333bfc32bafa0af6c874f4e8530bcaabf25d1578b97"},"schema_version":"1.0","source":{"id":"2205.10964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10964","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10964v2","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10964","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"6EQ3SFQQONAG","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"6EQ3SFQQONAGEZJA","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"6EQ3SFQQ","created_at":"2026-07-05T05:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:642778b7aadea5d69e4629aa52e5fd2ea103b32acedd8cbfa56b4aacd4ef832d","target":"graph","created_at":"2026-07-05T05:09:18Z","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/2205.10964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We assess how multilingual language models maintain a shared multilingual representation space while still encoding language-sensitive information in each language. Using XLM-R as a case study, we show that languages occupy similar linear subspaces after mean-centering, evaluated based on causal effects on language modeling performance and direct comparisons between subspaces for 88 languages. The subspace means differ along language-sensitive axes that are relatively stable throughout middle layers, and these axes encode information such as token vocabularies. Shifting representations by lang","authors_text":"Benjamin K. Bergen, Tyler A. Chang, Zhuowen Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-22T23:58:24Z","title":"The Geometry of Multilingual Language Model Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10964","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":"sha256:8ad6b8d345f729624fb45cf93a8566b0054368e36783e601d92db8fafdbe148e","target":"record","created_at":"2026-07-05T05:09:18Z","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":"b997132c0461c00a4aa744540313875745fc5f647698b7a611636108a4c76ad2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-22T23:58:24Z","title_canon_sha256":"be83bf7ccda1f39c801fc333bfc32bafa0af6c874f4e8530bcaabf25d1578b97"},"schema_version":"1.0","source":{"id":"2205.10964","kind":"arxiv","version":2}},"canonical_sha256":"f121b9161073406265206a7ae4ca4ac368a05a1d1cf42659621153463748c6e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f121b9161073406265206a7ae4ca4ac368a05a1d1cf42659621153463748c6e3","first_computed_at":"2026-07-05T05:09:18.256911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:18.256911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eXq+Hhq7E9A5/jLYMBD8mT1TRS8qoI4OFMwcChJD1cTkNk68Y7l9UzrPobzHj8ExliM6QBYyUT08vzvtGb4wBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:18.257248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ad6b8d345f729624fb45cf93a8566b0054368e36783e601d92db8fafdbe148e","sha256:642778b7aadea5d69e4629aa52e5fd2ea103b32acedd8cbfa56b4aacd4ef832d"],"state_sha256":"b84777248a788399b3ce1555cec9e2a78e7ff1fc45e0e30a05662b1c2de74b19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9JW5Q8W5MaYrpdoPO7gFeKWnilGJWKYsUb4XwxruFqUCJqzbG+SbB4ePGiMUhaQ+b2j7GhbeXGCkWT9V89fBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:58:11.664322Z","bundle_sha256":"2fc714deef054af361dcaae6791b0d20b16d0510724485d2824f515a3641d529"}}