{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ULBQLMH3GPUDHOLMYLKAWVWU6D","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":"828b41d62da5a677952996231cc2def3f07eeee41e2feee127b5a8e51e732de8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-06T13:27:26Z","title_canon_sha256":"a0b627cfbd43fe73d3ee8eb64d43c03d8afdf01c3eb532b1457c15ccd8e49676"},"schema_version":"1.0","source":{"id":"2206.02608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02608","created_at":"2026-07-05T04:29:19Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02608v1","created_at":"2026-07-05T04:29:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02608","created_at":"2026-07-05T04:29:19Z"},{"alias_kind":"pith_short_12","alias_value":"ULBQLMH3GPUD","created_at":"2026-07-05T04:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"ULBQLMH3GPUDHOLM","created_at":"2026-07-05T04:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"ULBQLMH3","created_at":"2026-07-05T04:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:785725e857dfca13f2c6083387cde0237c448d06a4b789b79431f66719d93c4f","target":"graph","created_at":"2026-07-05T04:29:19Z","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/2206.02608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens. Here, studying a range of models (e.g., GPT- J, BERT, RoBERTa, GloVe), we probe what word pieces encode about character-level information by training classifiers to predict the presence or absence of a particular alphabetical character in a token, based on its embedding (e.g., probing whether the model embedding for \"cat\" encodes that it contains the character \"a\"). W","authors_text":"Ayush Kaushal, Kyle Mahowald","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-06T13:27:26Z","title":"What do tokens know about their characters and how do they know it?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02608","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":"sha256:4f0a5cb17f57b067c90e67f304708d817b78a1e6a8810f06205a4850bedcaf5c","target":"record","created_at":"2026-07-05T04:29:19Z","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":"828b41d62da5a677952996231cc2def3f07eeee41e2feee127b5a8e51e732de8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-06T13:27:26Z","title_canon_sha256":"a0b627cfbd43fe73d3ee8eb64d43c03d8afdf01c3eb532b1457c15ccd8e49676"},"schema_version":"1.0","source":{"id":"2206.02608","kind":"arxiv","version":1}},"canonical_sha256":"a2c305b0fb33e833b96cc2d40b56d4f0eea99af9816e3b83a636931d6f24aa62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2c305b0fb33e833b96cc2d40b56d4f0eea99af9816e3b83a636931d6f24aa62","first_computed_at":"2026-07-05T04:29:19.565044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:19.565044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9DTl7EXk0HzVTlxxAwvEKL4y3AiBoElSCdr97Tbh1xjut70FIl0DR6EG3WgQw85q1CQv+7d4Qk+RLoRapyfMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:19.565530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f0a5cb17f57b067c90e67f304708d817b78a1e6a8810f06205a4850bedcaf5c","sha256:785725e857dfca13f2c6083387cde0237c448d06a4b789b79431f66719d93c4f"],"state_sha256":"e0c413e38123366295cf774e6cca9266c9ea0438e1ab61e5bb0c78dfae90bf6d"}