{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GTVLPSKMDC7LU6A2BZGOVTYVV2","short_pith_number":"pith:GTVLPSKM","canonical_record":{"source":{"id":"1804.08881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-24T07:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"f68e9fd34108c85212c8c6c6ba840825605bffb4078daf6c94dff6d875205be1","abstract_canon_sha256":"36488c7c156deaa760f5dcb687581ed609a087e22571cd987db182108387ea11"},"schema_version":"1.0"},"canonical_sha256":"34eab7c94c18beba781a0e4ceacf15ae951a66d58627dd992a9f119c32db081c","source":{"kind":"arxiv","id":"1804.08881","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08881","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08881v1","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08881","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"GTVLPSKMDC7L","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GTVLPSKMDC7LU6A2","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GTVLPSKM","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GTVLPSKMDC7LU6A2BZGOVTYVV2","target":"record","payload":{"canonical_record":{"source":{"id":"1804.08881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-24T07:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"f68e9fd34108c85212c8c6c6ba840825605bffb4078daf6c94dff6d875205be1","abstract_canon_sha256":"36488c7c156deaa760f5dcb687581ed609a087e22571cd987db182108387ea11"},"schema_version":"1.0"},"canonical_sha256":"34eab7c94c18beba781a0e4ceacf15ae951a66d58627dd992a9f119c32db081c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:37.011345Z","signature_b64":"C+/pNx+LdDHFpwILUjbakob9YK/xll4Q/jBH2CqD2gyECRLAzIekQQ3QgK+l5N3ZsG1PR+sgRIrmQtiI+ZsCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34eab7c94c18beba781a0e4ceacf15ae951a66d58627dd992a9f119c32db081c","last_reissued_at":"2026-05-18T00:17:37.010610Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:37.010610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.08881","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":"2026-05-18T00:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LnxjZjnQKh/9TxO7+KlPvKehwN3up4VPwQQlxiVbF/SAfevS3Q3NHkdFYnhLhsQuJlElw6KWOWGALHchLpqGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T11:24:53.402213Z"},"content_sha256":"dba2b2c61984332a0382ffb42515ce46b4b99bd1b16cc5b58821df4085175a28","schema_version":"1.0","event_id":"sha256:dba2b2c61984332a0382ffb42515ce46b4b99bd1b16cc5b58821df4085175a28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GTVLPSKMDC7LU6A2BZGOVTYVV2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing Language Models with Scaling Properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kumiko Tanaka-Ishii, Shuntaro Takahashi","submitted_at":"2018-04-24T07:58:20Z","abstract_excerpt":"Language models have primarily been evaluated with perplexity. While perplexity quantifies the most comprehensible prediction performance, it does not provide qualitative information on the success or failure of models. Another approach for evaluating language models is thus proposed, using the scaling properties of natural language. Five such tests are considered, with the first two accounting for the vocabulary population and the other three for the long memory of natural language. The following models were evaluated with these tests: n-grams, probabilistic context-free grammar (PCFG), Simon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08881","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":"2026-05-18T00:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SO1+dmjJbJ1tuaNeHxO6roGxrpJpbN+zIDprEYYqlTwxjoCieuiJMdTi4idWBvaNzpt24VMpggawBRsGI1bZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T11:24:53.402575Z"},"content_sha256":"d8961f0e28573b06edf641dfae03076103a5036c20b97487b8acf0f439e798ac","schema_version":"1.0","event_id":"sha256:d8961f0e28573b06edf641dfae03076103a5036c20b97487b8acf0f439e798ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTVLPSKMDC7LU6A2BZGOVTYVV2/bundle.json","state_url":"https://pith.science/pith/GTVLPSKMDC7LU6A2BZGOVTYVV2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTVLPSKMDC7LU6A2BZGOVTYVV2/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":"2026-06-03T11:24:53Z","links":{"resolver":"https://pith.science/pith/GTVLPSKMDC7LU6A2BZGOVTYVV2","bundle":"https://pith.science/pith/GTVLPSKMDC7LU6A2BZGOVTYVV2/bundle.json","state":"https://pith.science/pith/GTVLPSKMDC7LU6A2BZGOVTYVV2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTVLPSKMDC7LU6A2BZGOVTYVV2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GTVLPSKMDC7LU6A2BZGOVTYVV2","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":"36488c7c156deaa760f5dcb687581ed609a087e22571cd987db182108387ea11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-24T07:58:20Z","title_canon_sha256":"f68e9fd34108c85212c8c6c6ba840825605bffb4078daf6c94dff6d875205be1"},"schema_version":"1.0","source":{"id":"1804.08881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08881","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08881v1","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08881","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"GTVLPSKMDC7L","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GTVLPSKMDC7LU6A2","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GTVLPSKM","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:d8961f0e28573b06edf641dfae03076103a5036c20b97487b8acf0f439e798ac","target":"graph","created_at":"2026-05-18T00:17:37Z","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":"Language models have primarily been evaluated with perplexity. While perplexity quantifies the most comprehensible prediction performance, it does not provide qualitative information on the success or failure of models. Another approach for evaluating language models is thus proposed, using the scaling properties of natural language. Five such tests are considered, with the first two accounting for the vocabulary population and the other three for the long memory of natural language. The following models were evaluated with these tests: n-grams, probabilistic context-free grammar (PCFG), Simon","authors_text":"Kumiko Tanaka-Ishii, Shuntaro Takahashi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-24T07:58:20Z","title":"Assessing Language Models with Scaling Properties"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08881","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:dba2b2c61984332a0382ffb42515ce46b4b99bd1b16cc5b58821df4085175a28","target":"record","created_at":"2026-05-18T00:17:37Z","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":"36488c7c156deaa760f5dcb687581ed609a087e22571cd987db182108387ea11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-24T07:58:20Z","title_canon_sha256":"f68e9fd34108c85212c8c6c6ba840825605bffb4078daf6c94dff6d875205be1"},"schema_version":"1.0","source":{"id":"1804.08881","kind":"arxiv","version":1}},"canonical_sha256":"34eab7c94c18beba781a0e4ceacf15ae951a66d58627dd992a9f119c32db081c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34eab7c94c18beba781a0e4ceacf15ae951a66d58627dd992a9f119c32db081c","first_computed_at":"2026-05-18T00:17:37.010610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:37.010610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C+/pNx+LdDHFpwILUjbakob9YK/xll4Q/jBH2CqD2gyECRLAzIekQQ3QgK+l5N3ZsG1PR+sgRIrmQtiI+ZsCAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:37.011345Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.08881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dba2b2c61984332a0382ffb42515ce46b4b99bd1b16cc5b58821df4085175a28","sha256:d8961f0e28573b06edf641dfae03076103a5036c20b97487b8acf0f439e798ac"],"state_sha256":"19e7d037222f235310d87f01c8a88e83f07e8326c917bb1f3e5e817d3a78fd8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+t/4usTwc59U6s7nNu9pWvyOy9UIEW6EHaKa3+DOz2VRUPYOT+ZVFanyCYurFiUsoQNxI24PVzI1gXW6/GoEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T11:24:53.404559Z","bundle_sha256":"cfe2102bf5c2349c59e26f5e456cb7c9a3440fd6930ca05f32dc10aa3283ca58"}}