{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZAUXSGPQWAFCIHOFA7YH36HNXE","short_pith_number":"pith:ZAUXSGPQ","canonical_record":{"source":{"id":"2102.10864","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-22T09:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"8bf13fee02d399ee2e4ea6a7e51ac12eec40e516aaff8bad35089ee887623651","abstract_canon_sha256":"97f001fc36b5df9579caa9c90771583f8e2c6322ebf2e37a953ef8aab1424b3f"},"schema_version":"1.0"},"canonical_sha256":"c8297919f0b00a241dc507f07df8edb92d91b05fdfffbd065163a2f1afa50aca","source":{"kind":"arxiv","id":"2102.10864","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10864","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10864v2","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10864","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"pith_short_12","alias_value":"ZAUXSGPQWAFC","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZAUXSGPQWAFCIHOF","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZAUXSGPQ","created_at":"2026-07-05T02:26:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZAUXSGPQWAFCIHOFA7YH36HNXE","target":"record","payload":{"canonical_record":{"source":{"id":"2102.10864","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-22T09:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"8bf13fee02d399ee2e4ea6a7e51ac12eec40e516aaff8bad35089ee887623651","abstract_canon_sha256":"97f001fc36b5df9579caa9c90771583f8e2c6322ebf2e37a953ef8aab1424b3f"},"schema_version":"1.0"},"canonical_sha256":"c8297919f0b00a241dc507f07df8edb92d91b05fdfffbd065163a2f1afa50aca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:55.961420Z","signature_b64":"+gKbQTQ4y5FTn4m/+J/wNjgNNS/TXNTplFbwQe0Lvl7tHz2FLG4kCtVrg+RU9/SidZR8oWJkM7tCh5KoPkWNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8297919f0b00a241dc507f07df8edb92d91b05fdfffbd065163a2f1afa50aca","last_reissued_at":"2026-07-05T02:26:55.961034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:55.961034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.10864","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":"2026-07-05T02:26:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qcyda4Lh530ObSyeH6b3CtBxclC7j37gQNyRXoPCogYVZK8vqm34Q3feCiWLBl6jPiTR55B4hgSACCw23cIKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:27:37.976401Z"},"content_sha256":"bd66a42b233f0fec387be052a5bf110914ada3ceabb6627426b3ee492049b679","schema_version":"1.0","event_id":"sha256:bd66a42b233f0fec387be052a5bf110914ada3ceabb6627426b3ee492049b679"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZAUXSGPQWAFCIHOFA7YH36HNXE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subword Pooling Makes a Difference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"\\'Akos K\\'ad\\'ar, Andr\\'as Kornai, Judit \\'Acs","submitted_at":"2021-02-22T09:59:30Z","abstract_excerpt":"Contextual word-representations became a standard in modern natural language processing systems. These models use subword tokenization to handle large vocabularies and unknown words. Word-level usage of such systems requires a way of pooling multiple subwords that correspond to a single word. In this paper we investigate how the choice of subword pooling affects the downstream performance on three tasks: morphological probing, POS tagging and NER, in 9 typologically diverse languages. We compare these in two massively multilingual models, mBERT and XLM-RoBERTa. For morphological tasks, the wid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10864","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/2102.10864/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":"2026-07-05T02:26:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O3aMwPsyK7OA3aJ0zUD9nP9J/2kS15aPlz+MYYDtSTYBMpqxMkaQVRuIM8wJ8ZEMFpk0Nub9GhFyIjQxdXmwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:27:37.976900Z"},"content_sha256":"78b77a5a9a0609488b4d0353843aababcc82c95993b83e162a229091ded625b9","schema_version":"1.0","event_id":"sha256:78b77a5a9a0609488b4d0353843aababcc82c95993b83e162a229091ded625b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAUXSGPQWAFCIHOFA7YH36HNXE/bundle.json","state_url":"https://pith.science/pith/ZAUXSGPQWAFCIHOFA7YH36HNXE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAUXSGPQWAFCIHOFA7YH36HNXE/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":"2026-08-15T08:27:37Z","links":{"resolver":"https://pith.science/pith/ZAUXSGPQWAFCIHOFA7YH36HNXE","bundle":"https://pith.science/pith/ZAUXSGPQWAFCIHOFA7YH36HNXE/bundle.json","state":"https://pith.science/pith/ZAUXSGPQWAFCIHOFA7YH36HNXE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAUXSGPQWAFCIHOFA7YH36HNXE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZAUXSGPQWAFCIHOFA7YH36HNXE","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":"97f001fc36b5df9579caa9c90771583f8e2c6322ebf2e37a953ef8aab1424b3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-22T09:59:30Z","title_canon_sha256":"8bf13fee02d399ee2e4ea6a7e51ac12eec40e516aaff8bad35089ee887623651"},"schema_version":"1.0","source":{"id":"2102.10864","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10864","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10864v2","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10864","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"pith_short_12","alias_value":"ZAUXSGPQWAFC","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZAUXSGPQWAFCIHOF","created_at":"2026-07-05T02:26:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZAUXSGPQ","created_at":"2026-07-05T02:26:55Z"}],"graph_snapshots":[{"event_id":"sha256:78b77a5a9a0609488b4d0353843aababcc82c95993b83e162a229091ded625b9","target":"graph","created_at":"2026-07-05T02:26:55Z","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/2102.10864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contextual word-representations became a standard in modern natural language processing systems. These models use subword tokenization to handle large vocabularies and unknown words. Word-level usage of such systems requires a way of pooling multiple subwords that correspond to a single word. In this paper we investigate how the choice of subword pooling affects the downstream performance on three tasks: morphological probing, POS tagging and NER, in 9 typologically diverse languages. We compare these in two massively multilingual models, mBERT and XLM-RoBERTa. For morphological tasks, the wid","authors_text":"\\'Akos K\\'ad\\'ar, Andr\\'as Kornai, Judit \\'Acs","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-22T09:59:30Z","title":"Subword Pooling Makes a Difference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10864","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:bd66a42b233f0fec387be052a5bf110914ada3ceabb6627426b3ee492049b679","target":"record","created_at":"2026-07-05T02:26:55Z","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":"97f001fc36b5df9579caa9c90771583f8e2c6322ebf2e37a953ef8aab1424b3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-22T09:59:30Z","title_canon_sha256":"8bf13fee02d399ee2e4ea6a7e51ac12eec40e516aaff8bad35089ee887623651"},"schema_version":"1.0","source":{"id":"2102.10864","kind":"arxiv","version":2}},"canonical_sha256":"c8297919f0b00a241dc507f07df8edb92d91b05fdfffbd065163a2f1afa50aca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8297919f0b00a241dc507f07df8edb92d91b05fdfffbd065163a2f1afa50aca","first_computed_at":"2026-07-05T02:26:55.961034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:55.961034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+gKbQTQ4y5FTn4m/+J/wNjgNNS/TXNTplFbwQe0Lvl7tHz2FLG4kCtVrg+RU9/SidZR8oWJkM7tCh5KoPkWNBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:55.961420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10864","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd66a42b233f0fec387be052a5bf110914ada3ceabb6627426b3ee492049b679","sha256:78b77a5a9a0609488b4d0353843aababcc82c95993b83e162a229091ded625b9"],"state_sha256":"d9d7c3436190f04335167e1d55723fa74c4771664e2fc0b23f1d6787f0b82a8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fd4xZU+nM/lm9WhQopII+TrS1LjlvzbKQKL5WM+huOtY1g1yaGKyDaDgGCYy3gWVCPE6bBPcF3WOZH8uZsJMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T08:27:37.980750Z","bundle_sha256":"3eb05ee82128e41dcd15e44fa262ff4172ab618fd4035ddbe42023c02ffbe6eb"}}