{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YZ5ASFTYRFOOIJ7QOKSR4EJWC5","short_pith_number":"pith:YZ5ASFTY","canonical_record":{"source":{"id":"2412.11940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:24:58Z","cross_cats_sorted":[],"title_canon_sha256":"062a54d490a517d5bb861bf8cf2ba96772c3add1bb0c6d51954bacf8ef34a551","abstract_canon_sha256":"c11a65a78ce790df2fb67e9b237766567a5a4bea626091d4b782a70b12fc32dd"},"schema_version":"1.0"},"canonical_sha256":"c67a091678895ce427f072a51e113617536e60454ce8cc1a6de05ee1f4e25aaf","source":{"kind":"arxiv","id":"2412.11940","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11940","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11940v2","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11940","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"YZ5ASFTYRFOO","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"YZ5ASFTYRFOOIJ7Q","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"YZ5ASFTY","created_at":"2026-07-05T11:13:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YZ5ASFTYRFOOIJ7QOKSR4EJWC5","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:24:58Z","cross_cats_sorted":[],"title_canon_sha256":"062a54d490a517d5bb861bf8cf2ba96772c3add1bb0c6d51954bacf8ef34a551","abstract_canon_sha256":"c11a65a78ce790df2fb67e9b237766567a5a4bea626091d4b782a70b12fc32dd"},"schema_version":"1.0"},"canonical_sha256":"c67a091678895ce427f072a51e113617536e60454ce8cc1a6de05ee1f4e25aaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:17.019708Z","signature_b64":"6YwEwTAqa6dj+JB0c1sQ8+S0C1s5+xh+IpiWcJ8tambQZX2oiU/A2WvqZH01rNv+CxQzPPTGnVWd1Oo073VlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c67a091678895ce427f072a51e113617536e60454ce8cc1a6de05ee1f4e25aaf","last_reissued_at":"2026-07-05T11:13:17.019185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:17.019185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11940","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":"2026-07-05T11:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZWOD990bWZE6l3RRetl6R/m/6kDK5tZuTwCeXQ4PHtYxnfWDbxPmWltxliUEbF6fXVKPCvG8TOyrtFd6yYE9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:15:30.603893Z"},"content_sha256":"ed9bd0a2b97de8c25b368c6d8f36632dc57d278053d1058ab7b7ece636122626","schema_version":"1.0","event_id":"sha256:ed9bd0a2b97de8c25b368c6d8f36632dc57d278053d1058ab7b7ece636122626"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YZ5ASFTYRFOOIJ7QOKSR4EJWC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Impact of Token Granularity on the Predictive Power of Language Model Surprisal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Byung-Doh Oh, William Schuler","submitted_at":"2024-12-16T16:24:58Z","abstract_excerpt":"Word-by-word language model surprisal is often used to model the incremental processing of human readers, which raises questions about how various choices in language modeling influence its predictive power. One factor that has been overlooked in cognitive modeling is the granularity of subword tokens, which explicitly encodes information about word length and frequency, and ultimately influences the quality of vector representations that are learned. This paper presents experiments that manipulate the token granularity and evaluate its impact on the ability of surprisal to account for process"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11940","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/2412.11940/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":"2026-07-05T11:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kfKZBQ5Jlt1U9An3wrKTh++w7hbY2XQEZMrS9ctU0ftQO/7AbXtH+Fw1lTMHUVaAG15L44jX5zgkVX9RWs9bBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:15:30.604851Z"},"content_sha256":"18943492dca2cb3ac60c9b5d37a0358c0e6426f953d3afc5185afb702118a0c8","schema_version":"1.0","event_id":"sha256:18943492dca2cb3ac60c9b5d37a0358c0e6426f953d3afc5185afb702118a0c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZ5ASFTYRFOOIJ7QOKSR4EJWC5/bundle.json","state_url":"https://pith.science/pith/YZ5ASFTYRFOOIJ7QOKSR4EJWC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZ5ASFTYRFOOIJ7QOKSR4EJWC5/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":"2026-08-21T15:15:30Z","links":{"resolver":"https://pith.science/pith/YZ5ASFTYRFOOIJ7QOKSR4EJWC5","bundle":"https://pith.science/pith/YZ5ASFTYRFOOIJ7QOKSR4EJWC5/bundle.json","state":"https://pith.science/pith/YZ5ASFTYRFOOIJ7QOKSR4EJWC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZ5ASFTYRFOOIJ7QOKSR4EJWC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YZ5ASFTYRFOOIJ7QOKSR4EJWC5","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":"c11a65a78ce790df2fb67e9b237766567a5a4bea626091d4b782a70b12fc32dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:24:58Z","title_canon_sha256":"062a54d490a517d5bb861bf8cf2ba96772c3add1bb0c6d51954bacf8ef34a551"},"schema_version":"1.0","source":{"id":"2412.11940","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11940","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11940v2","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11940","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"YZ5ASFTYRFOO","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"YZ5ASFTYRFOOIJ7Q","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"YZ5ASFTY","created_at":"2026-07-05T11:13:17Z"}],"graph_snapshots":[{"event_id":"sha256:18943492dca2cb3ac60c9b5d37a0358c0e6426f953d3afc5185afb702118a0c8","target":"graph","created_at":"2026-07-05T11:13:17Z","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/2412.11940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word-by-word language model surprisal is often used to model the incremental processing of human readers, which raises questions about how various choices in language modeling influence its predictive power. One factor that has been overlooked in cognitive modeling is the granularity of subword tokens, which explicitly encodes information about word length and frequency, and ultimately influences the quality of vector representations that are learned. This paper presents experiments that manipulate the token granularity and evaluate its impact on the ability of surprisal to account for process","authors_text":"Byung-Doh Oh, William Schuler","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:24:58Z","title":"The Impact of Token Granularity on the Predictive Power of Language Model Surprisal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11940","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:ed9bd0a2b97de8c25b368c6d8f36632dc57d278053d1058ab7b7ece636122626","target":"record","created_at":"2026-07-05T11:13:17Z","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":"c11a65a78ce790df2fb67e9b237766567a5a4bea626091d4b782a70b12fc32dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:24:58Z","title_canon_sha256":"062a54d490a517d5bb861bf8cf2ba96772c3add1bb0c6d51954bacf8ef34a551"},"schema_version":"1.0","source":{"id":"2412.11940","kind":"arxiv","version":2}},"canonical_sha256":"c67a091678895ce427f072a51e113617536e60454ce8cc1a6de05ee1f4e25aaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c67a091678895ce427f072a51e113617536e60454ce8cc1a6de05ee1f4e25aaf","first_computed_at":"2026-07-05T11:13:17.019185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:17.019185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6YwEwTAqa6dj+JB0c1sQ8+S0C1s5+xh+IpiWcJ8tambQZX2oiU/A2WvqZH01rNv+CxQzPPTGnVWd1Oo073VlBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:17.019708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11940","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed9bd0a2b97de8c25b368c6d8f36632dc57d278053d1058ab7b7ece636122626","sha256:18943492dca2cb3ac60c9b5d37a0358c0e6426f953d3afc5185afb702118a0c8"],"state_sha256":"841746022d9cf49ce030efa7b2bca736697db29e956083070407537327dcaa7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CepL2PpuRho5L7KTNfRFd4swifFlthiTyYTbyCD0JWfFtVzvLkddnKbp6XZqWxnHZQ/an/8wtkrv3gr0CjxfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:15:30.612245Z","bundle_sha256":"af67f4228d2dd73c38d0920d3da7f7b7d651ce5fc401cf3ba69afa44ba7ad0c8"}}