{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:X4B3WDFZEAEI6TJGVNOPWB24WB","short_pith_number":"pith:X4B3WDFZ","canonical_record":{"source":{"id":"1905.09139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-22T13:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"2b102c2614dd165ce69f97f5631ebc3dccda15f977f4fd15ee302a29277ba5cf","abstract_canon_sha256":"c9aa2e838907bfc02481f90f28eddbf2a0557574ac82d96143c362cae092cb25"},"schema_version":"1.0"},"canonical_sha256":"bf03bb0cb920088f4d26ab5cfb075cb04a03f94a4cdda8762e167d72b4e5f7ee","source":{"kind":"arxiv","id":"1905.09139","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09139","created_at":"2026-05-17T23:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09139v1","created_at":"2026-05-17T23:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09139","created_at":"2026-05-17T23:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"X4B3WDFZEAEI","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X4B3WDFZEAEI6TJG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X4B3WDFZ","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:X4B3WDFZEAEI6TJGVNOPWB24WB","target":"record","payload":{"canonical_record":{"source":{"id":"1905.09139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-22T13:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"2b102c2614dd165ce69f97f5631ebc3dccda15f977f4fd15ee302a29277ba5cf","abstract_canon_sha256":"c9aa2e838907bfc02481f90f28eddbf2a0557574ac82d96143c362cae092cb25"},"schema_version":"1.0"},"canonical_sha256":"bf03bb0cb920088f4d26ab5cfb075cb04a03f94a4cdda8762e167d72b4e5f7ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:21.886098Z","signature_b64":"MqO7U++8JNsdIOJgZw4Sq66ZJ7cfIQ37yESTmWrnOSSjbjAOLkqn07eYcl5Du5ctJ/+gJBrowkm60RMgx22kDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf03bb0cb920088f4d26ab5cfb075cb04a03f94a4cdda8762e167d72b4e5f7ee","last_reissued_at":"2026-05-17T23:45:21.885456Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:21.885456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.09139","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":"2026-05-17T23:45:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPqS+40jmkEEqOCgMs3wVe+GEbjPB1pKDDi+QpqfmxMm3Mg4bEX5lcgoleE/u73M3/UN/slRCziyxryAwHPEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:40.836419Z"},"content_sha256":"2258f6e23c4a15d12f9ce482c12d643eda5365f3b9d4957968ecfcb1bd59d6c9","schema_version":"1.0","event_id":"sha256:2258f6e23c4a15d12f9ce482c12d643eda5365f3b9d4957968ecfcb1bd59d6c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:X4B3WDFZEAEI6TJGVNOPWB24WB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sentence Length","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'as Kornai, G\\'abor Borb\\'ely","submitted_at":"2019-05-22T13:45:05Z","abstract_excerpt":"The distribution of sentence length in ordinary language is not well captured by the existing models. Here we survey previous models of sentence length and present our random walk model that offers both a better fit with the data and a better understanding of the distribution. We develop a generalization of KL divergence, discuss measuring the noise inherent in a corpus, and present a hyperparameter-free Bayesian model comparison method that has strong conceptual ties to Minimal Description Length modeling. The models we obtain require only a few dozen bits, orders of magnitude less than the n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09139","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":""},"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":"2026-05-17T23:45:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kw0Mqjy6frOp83qY6KdRGVisurMTjRraVMCxLgPy5+CZYyGw2G5Y+/iLeX0hMPP4CGQfG97+F0PypuUJio03Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:40.836915Z"},"content_sha256":"a5a80c33ff03abaf0e7df2a3bfa2d106bf5f173bf578225e70105ea7df996f56","schema_version":"1.0","event_id":"sha256:a5a80c33ff03abaf0e7df2a3bfa2d106bf5f173bf578225e70105ea7df996f56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4B3WDFZEAEI6TJGVNOPWB24WB/bundle.json","state_url":"https://pith.science/pith/X4B3WDFZEAEI6TJGVNOPWB24WB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4B3WDFZEAEI6TJGVNOPWB24WB/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":"2026-08-08T10:22:40Z","links":{"resolver":"https://pith.science/pith/X4B3WDFZEAEI6TJGVNOPWB24WB","bundle":"https://pith.science/pith/X4B3WDFZEAEI6TJGVNOPWB24WB/bundle.json","state":"https://pith.science/pith/X4B3WDFZEAEI6TJGVNOPWB24WB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4B3WDFZEAEI6TJGVNOPWB24WB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X4B3WDFZEAEI6TJGVNOPWB24WB","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":"c9aa2e838907bfc02481f90f28eddbf2a0557574ac82d96143c362cae092cb25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-22T13:45:05Z","title_canon_sha256":"2b102c2614dd165ce69f97f5631ebc3dccda15f977f4fd15ee302a29277ba5cf"},"schema_version":"1.0","source":{"id":"1905.09139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09139","created_at":"2026-05-17T23:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09139v1","created_at":"2026-05-17T23:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09139","created_at":"2026-05-17T23:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"X4B3WDFZEAEI","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X4B3WDFZEAEI6TJG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X4B3WDFZ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:a5a80c33ff03abaf0e7df2a3bfa2d106bf5f173bf578225e70105ea7df996f56","target":"graph","created_at":"2026-05-17T23:45:21Z","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"},"paper":{"abstract_excerpt":"The distribution of sentence length in ordinary language is not well captured by the existing models. Here we survey previous models of sentence length and present our random walk model that offers both a better fit with the data and a better understanding of the distribution. We develop a generalization of KL divergence, discuss measuring the noise inherent in a corpus, and present a hyperparameter-free Bayesian model comparison method that has strong conceptual ties to Minimal Description Length modeling. The models we obtain require only a few dozen bits, orders of magnitude less than the n","authors_text":"Andr\\'as Kornai, G\\'abor Borb\\'ely","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-22T13:45:05Z","title":"Sentence Length"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09139","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":"sha256:2258f6e23c4a15d12f9ce482c12d643eda5365f3b9d4957968ecfcb1bd59d6c9","target":"record","created_at":"2026-05-17T23:45:21Z","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":"c9aa2e838907bfc02481f90f28eddbf2a0557574ac82d96143c362cae092cb25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-22T13:45:05Z","title_canon_sha256":"2b102c2614dd165ce69f97f5631ebc3dccda15f977f4fd15ee302a29277ba5cf"},"schema_version":"1.0","source":{"id":"1905.09139","kind":"arxiv","version":1}},"canonical_sha256":"bf03bb0cb920088f4d26ab5cfb075cb04a03f94a4cdda8762e167d72b4e5f7ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf03bb0cb920088f4d26ab5cfb075cb04a03f94a4cdda8762e167d72b4e5f7ee","first_computed_at":"2026-05-17T23:45:21.885456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:21.885456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MqO7U++8JNsdIOJgZw4Sq66ZJ7cfIQ37yESTmWrnOSSjbjAOLkqn07eYcl5Du5ctJ/+gJBrowkm60RMgx22kDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:21.886098Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.09139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2258f6e23c4a15d12f9ce482c12d643eda5365f3b9d4957968ecfcb1bd59d6c9","sha256:a5a80c33ff03abaf0e7df2a3bfa2d106bf5f173bf578225e70105ea7df996f56"],"state_sha256":"676629ac8cb7c6af0d6f523f2828bfa26b534940492c25807d6d9265e886e45c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cj/AbuaGZFD9FKWoKlt9sygvQz3AYwLYOVKuFd3Pfkw0BXh1E5zcOxgezBVC7coAwNm/csT/BVK1AyYBqVgSCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:22:40.841818Z","bundle_sha256":"29a97764a09acac84531c509220e8f86e874e6d0cc36194054cf9c01c537aac4"}}