{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KW7RDYWGC3FHUAZSLC4GKK3BPN","short_pith_number":"pith:KW7RDYWG","canonical_record":{"source":{"id":"2402.09808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T09:14:53Z","cross_cats_sorted":[],"title_canon_sha256":"589f6fec4bcae3462aa838ae9093677603a9c806e7dd221523d034b064c3284d","abstract_canon_sha256":"00dd1a4141af7cde26efe9d9e14ba929959919f6b9d2af9771b5b1fba93e3eb4"},"schema_version":"1.0"},"canonical_sha256":"55bf11e2c616ca7a033258b8652b617b78b2145f2424d24732c371ee22747d23","source":{"kind":"arxiv","id":"2402.09808","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09808","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09808v2","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09808","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"KW7RDYWGC3FH","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"pith_short_16","alias_value":"KW7RDYWGC3FHUAZS","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"pith_short_8","alias_value":"KW7RDYWG","created_at":"2026-07-05T07:48:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KW7RDYWGC3FHUAZSLC4GKK3BPN","target":"record","payload":{"canonical_record":{"source":{"id":"2402.09808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T09:14:53Z","cross_cats_sorted":[],"title_canon_sha256":"589f6fec4bcae3462aa838ae9093677603a9c806e7dd221523d034b064c3284d","abstract_canon_sha256":"00dd1a4141af7cde26efe9d9e14ba929959919f6b9d2af9771b5b1fba93e3eb4"},"schema_version":"1.0"},"canonical_sha256":"55bf11e2c616ca7a033258b8652b617b78b2145f2424d24732c371ee22747d23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:03.706002Z","signature_b64":"0PtwPu9LJo7vjYdGFraTOPxWI3f3PRSYC21UzLGTduChKfQTnaQV/o0WQOV8rCgsnhoWWYc0sRBlJBB1thmBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55bf11e2c616ca7a033258b8652b617b78b2145f2424d24732c371ee22747d23","last_reissued_at":"2026-07-05T07:48:03.705465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:03.705465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.09808","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":"2026-07-05T07:48:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tUe/AgnwfX1Sz7tTCcKqW19xtwmMXhz6/15rrf34jRYxl2wLlzA0Xz94/n3p6rj54BUgPatACfdOqGCzZCkWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:28:45.899497Z"},"content_sha256":"5622732a35d9e76810c14c5e3e061f3da9f87dd55729694116c8a38f0160770a","schema_version":"1.0","event_id":"sha256:5622732a35d9e76810c14c5e3e061f3da9f87dd55729694116c8a38f0160770a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KW7RDYWGC3FHUAZSLC4GKK3BPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge of Pretrained Language Models on Surface Information of Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Naoaki Okazaki, Tatsuya Hiraoka","submitted_at":"2024-02-15T09:14:53Z","abstract_excerpt":"Do pretrained language models have knowledge regarding the surface information of tokens? We examined the surface information stored in word or subword embeddings acquired by pretrained language models from the perspectives of token length, substrings, and token constitution. Additionally, we evaluated the ability of models to generate knowledge regarding token surfaces. We focused on 12 pretrained language models that were mainly trained on English and Japanese corpora. Experimental results demonstrate that pretrained language models have knowledge regarding token length and substrings but no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09808","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/2402.09808/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":"2026-07-05T07:48:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bO5gsk5FB0k7op3NSePIJNVH68iUWV4DdJT8tdXHgyJBlxjw4QrYkRcOTCMW06zKKtru6fAPofZTcpKPMLNfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:28:45.899992Z"},"content_sha256":"9686f9aa3a730ce840aa6f7b577240ac7d62feb8723afa19c9b0592ce83c2fbb","schema_version":"1.0","event_id":"sha256:9686f9aa3a730ce840aa6f7b577240ac7d62feb8723afa19c9b0592ce83c2fbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KW7RDYWGC3FHUAZSLC4GKK3BPN/bundle.json","state_url":"https://pith.science/pith/KW7RDYWGC3FHUAZSLC4GKK3BPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KW7RDYWGC3FHUAZSLC4GKK3BPN/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":"2026-08-14T07:28:45Z","links":{"resolver":"https://pith.science/pith/KW7RDYWGC3FHUAZSLC4GKK3BPN","bundle":"https://pith.science/pith/KW7RDYWGC3FHUAZSLC4GKK3BPN/bundle.json","state":"https://pith.science/pith/KW7RDYWGC3FHUAZSLC4GKK3BPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KW7RDYWGC3FHUAZSLC4GKK3BPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KW7RDYWGC3FHUAZSLC4GKK3BPN","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":"00dd1a4141af7cde26efe9d9e14ba929959919f6b9d2af9771b5b1fba93e3eb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T09:14:53Z","title_canon_sha256":"589f6fec4bcae3462aa838ae9093677603a9c806e7dd221523d034b064c3284d"},"schema_version":"1.0","source":{"id":"2402.09808","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09808","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09808v2","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09808","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"KW7RDYWGC3FH","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"pith_short_16","alias_value":"KW7RDYWGC3FHUAZS","created_at":"2026-07-05T07:48:03Z"},{"alias_kind":"pith_short_8","alias_value":"KW7RDYWG","created_at":"2026-07-05T07:48:03Z"}],"graph_snapshots":[{"event_id":"sha256:9686f9aa3a730ce840aa6f7b577240ac7d62feb8723afa19c9b0592ce83c2fbb","target":"graph","created_at":"2026-07-05T07:48:03Z","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/2402.09808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Do pretrained language models have knowledge regarding the surface information of tokens? We examined the surface information stored in word or subword embeddings acquired by pretrained language models from the perspectives of token length, substrings, and token constitution. Additionally, we evaluated the ability of models to generate knowledge regarding token surfaces. We focused on 12 pretrained language models that were mainly trained on English and Japanese corpora. Experimental results demonstrate that pretrained language models have knowledge regarding token length and substrings but no","authors_text":"Naoaki Okazaki, Tatsuya Hiraoka","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T09:14:53Z","title":"Knowledge of Pretrained Language Models on Surface Information of Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09808","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":"sha256:5622732a35d9e76810c14c5e3e061f3da9f87dd55729694116c8a38f0160770a","target":"record","created_at":"2026-07-05T07:48:03Z","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":"00dd1a4141af7cde26efe9d9e14ba929959919f6b9d2af9771b5b1fba93e3eb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T09:14:53Z","title_canon_sha256":"589f6fec4bcae3462aa838ae9093677603a9c806e7dd221523d034b064c3284d"},"schema_version":"1.0","source":{"id":"2402.09808","kind":"arxiv","version":2}},"canonical_sha256":"55bf11e2c616ca7a033258b8652b617b78b2145f2424d24732c371ee22747d23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55bf11e2c616ca7a033258b8652b617b78b2145f2424d24732c371ee22747d23","first_computed_at":"2026-07-05T07:48:03.705465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:03.705465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0PtwPu9LJo7vjYdGFraTOPxWI3f3PRSYC21UzLGTduChKfQTnaQV/o0WQOV8rCgsnhoWWYc0sRBlJBB1thmBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:03.706002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09808","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5622732a35d9e76810c14c5e3e061f3da9f87dd55729694116c8a38f0160770a","sha256:9686f9aa3a730ce840aa6f7b577240ac7d62feb8723afa19c9b0592ce83c2fbb"],"state_sha256":"5a512b4395c3ed5cce3ca3257eaca3572ce84cb3c93f519677ba690c855f9639"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kfdljtsekk9L+lOqGgDIsPUbTaEOrhHRzszMmw+5rZx190muRx3p+Bt3Mrarg0hxuvXhWV5h++C2r9N+StSLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:28:45.903646Z","bundle_sha256":"52c7714372309f57b52f65d036bdf34017a2c50c7ce6bde761bea7d07048be70"}}