{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RAGETXC5EPG2HNWGIRJIKRYBZR","short_pith_number":"pith:RAGETXC5","canonical_record":{"source":{"id":"2009.12862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T15:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"73bae4bae93d8bc0bb24f6b151c47025e88c081b1a838d8f4fcb8080d42a4146","abstract_canon_sha256":"a749efd35442c7c3b37bf92bbcf9f054c2f8b564062e5160dde045ea3d22e1ea"},"schema_version":"1.0"},"canonical_sha256":"880c49dc5d23cda3b6c64452854701cc7dd92f6ebe3cba6278bcd1de308e1b7a","source":{"kind":"arxiv","id":"2009.12862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12862","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12862v1","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12862","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"pith_short_12","alias_value":"RAGETXC5EPG2","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"pith_short_16","alias_value":"RAGETXC5EPG2HNWG","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"pith_short_8","alias_value":"RAGETXC5","created_at":"2026-07-05T01:38:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RAGETXC5EPG2HNWGIRJIKRYBZR","target":"record","payload":{"canonical_record":{"source":{"id":"2009.12862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T15:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"73bae4bae93d8bc0bb24f6b151c47025e88c081b1a838d8f4fcb8080d42a4146","abstract_canon_sha256":"a749efd35442c7c3b37bf92bbcf9f054c2f8b564062e5160dde045ea3d22e1ea"},"schema_version":"1.0"},"canonical_sha256":"880c49dc5d23cda3b6c64452854701cc7dd92f6ebe3cba6278bcd1de308e1b7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:24.250140Z","signature_b64":"vMEBSZRt8wKHrzlCOYwKh+hvPjuZexCa8dPrEaOmWm2SKoF9/FjtREYI/y/AOjkAMmn3DRxU2DUmfqs1iN4tCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"880c49dc5d23cda3b6c64452854701cc7dd92f6ebe3cba6278bcd1de308e1b7a","last_reissued_at":"2026-07-05T01:38:24.249727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:24.249727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.12862","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":"2026-07-05T01:38:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zorxX8ZRgESVCJxbc41GL9EaVvKVEb9JUAyz4bu1WtbYG6ORfMq7cX1few3uas9y7ZASFTjT3vu1dNvSHr38CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:59:51.393513Z"},"content_sha256":"468b1e3083b58899e2a377453b557c15f782cf6ce69af6bfc9e5df08b45fe746","schema_version":"1.0","event_id":"sha256:468b1e3083b58899e2a377453b557c15f782cf6ce69af6bfc9e5df08b45fe746"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RAGETXC5EPG2HNWGIRJIKRYBZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Shutova, Rochelle Choenni","submitted_at":"2020-09-27T15:00:52Z","abstract_excerpt":"Multilingual sentence encoders have seen much success in cross-lingual model transfer for downstream NLP tasks. Yet, we know relatively little about the properties of individual languages or the general patterns of linguistic variation that they encode. We propose methods for probing sentence representations from state-of-the-art multilingual encoders (LASER, M-BERT, XLM and XLM-R) with respect to a range of typological properties pertaining to lexical, morphological and syntactic structure. In addition, we investigate how this information is distributed across all layers of the models. Our re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12862","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/2009.12862/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":"2026-07-05T01:38:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IWP9v6LJz020AWIKbXrlMVoD9P2b+sJFSpDobtQKP51Jo5qQYqGcVDTKkjGY/mOHAc9G6AO3b7XSrtF1HahKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:59:51.394504Z"},"content_sha256":"f570dfbba1a6e5159f7371db507fa639bb08b8f884cb95998b54ef9a3cff6b7a","schema_version":"1.0","event_id":"sha256:f570dfbba1a6e5159f7371db507fa639bb08b8f884cb95998b54ef9a3cff6b7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RAGETXC5EPG2HNWGIRJIKRYBZR/bundle.json","state_url":"https://pith.science/pith/RAGETXC5EPG2HNWGIRJIKRYBZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RAGETXC5EPG2HNWGIRJIKRYBZR/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":"2026-08-18T17:59:51Z","links":{"resolver":"https://pith.science/pith/RAGETXC5EPG2HNWGIRJIKRYBZR","bundle":"https://pith.science/pith/RAGETXC5EPG2HNWGIRJIKRYBZR/bundle.json","state":"https://pith.science/pith/RAGETXC5EPG2HNWGIRJIKRYBZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RAGETXC5EPG2HNWGIRJIKRYBZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RAGETXC5EPG2HNWGIRJIKRYBZR","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":"a749efd35442c7c3b37bf92bbcf9f054c2f8b564062e5160dde045ea3d22e1ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T15:00:52Z","title_canon_sha256":"73bae4bae93d8bc0bb24f6b151c47025e88c081b1a838d8f4fcb8080d42a4146"},"schema_version":"1.0","source":{"id":"2009.12862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12862","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12862v1","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12862","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"pith_short_12","alias_value":"RAGETXC5EPG2","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"pith_short_16","alias_value":"RAGETXC5EPG2HNWG","created_at":"2026-07-05T01:38:24Z"},{"alias_kind":"pith_short_8","alias_value":"RAGETXC5","created_at":"2026-07-05T01:38:24Z"}],"graph_snapshots":[{"event_id":"sha256:f570dfbba1a6e5159f7371db507fa639bb08b8f884cb95998b54ef9a3cff6b7a","target":"graph","created_at":"2026-07-05T01:38:24Z","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/2009.12862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual sentence encoders have seen much success in cross-lingual model transfer for downstream NLP tasks. Yet, we know relatively little about the properties of individual languages or the general patterns of linguistic variation that they encode. We propose methods for probing sentence representations from state-of-the-art multilingual encoders (LASER, M-BERT, XLM and XLM-R) with respect to a range of typological properties pertaining to lexical, morphological and syntactic structure. In addition, we investigate how this information is distributed across all layers of the models. Our re","authors_text":"Ekaterina Shutova, Rochelle Choenni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T15:00:52Z","title":"What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12862","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":"sha256:468b1e3083b58899e2a377453b557c15f782cf6ce69af6bfc9e5df08b45fe746","target":"record","created_at":"2026-07-05T01:38:24Z","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":"a749efd35442c7c3b37bf92bbcf9f054c2f8b564062e5160dde045ea3d22e1ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T15:00:52Z","title_canon_sha256":"73bae4bae93d8bc0bb24f6b151c47025e88c081b1a838d8f4fcb8080d42a4146"},"schema_version":"1.0","source":{"id":"2009.12862","kind":"arxiv","version":1}},"canonical_sha256":"880c49dc5d23cda3b6c64452854701cc7dd92f6ebe3cba6278bcd1de308e1b7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"880c49dc5d23cda3b6c64452854701cc7dd92f6ebe3cba6278bcd1de308e1b7a","first_computed_at":"2026-07-05T01:38:24.249727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:38:24.249727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vMEBSZRt8wKHrzlCOYwKh+hvPjuZexCa8dPrEaOmWm2SKoF9/FjtREYI/y/AOjkAMmn3DRxU2DUmfqs1iN4tCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:38:24.250140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.12862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:468b1e3083b58899e2a377453b557c15f782cf6ce69af6bfc9e5df08b45fe746","sha256:f570dfbba1a6e5159f7371db507fa639bb08b8f884cb95998b54ef9a3cff6b7a"],"state_sha256":"2cebd8e65ecb2ba1789425f2d616da3c8a3be6b127be0966f9dc9bbabd4366d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KNVSzJ7uf4xN+i5G5e0YwxRbeLy98J+aeqnziB5JVMmd2DJlHQ2izhGNeDGOTjLVmkqiEQ+Kqm6ISajKizKcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:59:51.402778Z","bundle_sha256":"19857cd6b351ac0f41253b9beb354b17f0837e0124d31248902e523a2a753dc5"}}