{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WUDNHOJBTFGQWK2YNMVA2I5B4G","short_pith_number":"pith:WUDNHOJB","canonical_record":{"source":{"id":"2011.13220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-26T10:39:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"45df09bdde7e2aac908885862688a22c1e8f1d35e9d851c74bd7d848f870e1a2","abstract_canon_sha256":"ebaccb540f2f6f165eeb03e8a382f67e6f193a84bdd5cdc6661b945c6d306c8d"},"schema_version":"1.0"},"canonical_sha256":"b506d3b921994d0b2b586b2a0d23a1e1bcc7110a3fd03950d0bb17f2a8a2428b","source":{"kind":"arxiv","id":"2011.13220","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13220","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13220v1","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13220","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"WUDNHOJBTFGQ","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_16","alias_value":"WUDNHOJBTFGQWK2Y","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_8","alias_value":"WUDNHOJB","created_at":"2026-07-05T01:54:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WUDNHOJBTFGQWK2YNMVA2I5B4G","target":"record","payload":{"canonical_record":{"source":{"id":"2011.13220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-26T10:39:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"45df09bdde7e2aac908885862688a22c1e8f1d35e9d851c74bd7d848f870e1a2","abstract_canon_sha256":"ebaccb540f2f6f165eeb03e8a382f67e6f193a84bdd5cdc6661b945c6d306c8d"},"schema_version":"1.0"},"canonical_sha256":"b506d3b921994d0b2b586b2a0d23a1e1bcc7110a3fd03950d0bb17f2a8a2428b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:54:52.094406Z","signature_b64":"HVvdiRecrvP06dSsBTchJMcj7jpqsK0GKP2sDbI8dGmzhNwv7e3qRY/rTwtRmcdvNdZmyi/2ZIzAQWcRXsLtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b506d3b921994d0b2b586b2a0d23a1e1bcc7110a3fd03950d0bb17f2a8a2428b","last_reissued_at":"2026-07-05T01:54:52.093852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:54:52.093852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.13220","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":"2026-07-05T01:54:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xg8L1fhl2wYt9QK3SYkiwB2z6IoFeVyskWXZNEzIO/hS6z2bK3prU5+m9+kQwz5pzGRVanJBp/SM8uTnQ27ACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:23:01.767046Z"},"content_sha256":"376a66c1fbd887508c11618f6f891a52b1381732cc926db29443a6566be06231","schema_version":"1.0","event_id":"sha256:376a66c1fbd887508c11618f6f891a52b1381732cc926db29443a6566be06231"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WUDNHOJBTFGQWK2YNMVA2I5B4G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unigram-Normalized Perplexity as a Language Model Performance Measure with Different Vocabulary Sizes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jihyeon Roh, Sang-Hoon Oh, Soo-Young Lee","submitted_at":"2020-11-26T10:39:03Z","abstract_excerpt":"Although Perplexity is a widely used performance metric for language models, the values are highly dependent upon the number of words in the corpus and is useful to compare performance of the same corpus only. In this paper, we propose a new metric that can be used to evaluate language model performance with different vocabulary sizes. The proposed unigram-normalized Perplexity actually presents the performance improvement of the language models from that of simple unigram model, and is robust on the vocabulary size. Both theoretical analysis and computational experiments are reported."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13220","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.13220/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":"2026-07-05T01:54:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZREYoZx/rWEzoLiuamJu3qLkRsjWgO+N89qX5FwyUhfoxci6+mvl5q7kQufnT08wh/vf/VIh+CjYz/dE70kAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:23:01.767552Z"},"content_sha256":"c83224adbc07fb497460d2ef381d79b78f336e2a04156100ae4d1ea429f3ef2e","schema_version":"1.0","event_id":"sha256:c83224adbc07fb497460d2ef381d79b78f336e2a04156100ae4d1ea429f3ef2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUDNHOJBTFGQWK2YNMVA2I5B4G/bundle.json","state_url":"https://pith.science/pith/WUDNHOJBTFGQWK2YNMVA2I5B4G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUDNHOJBTFGQWK2YNMVA2I5B4G/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":"2026-08-08T16:23:01Z","links":{"resolver":"https://pith.science/pith/WUDNHOJBTFGQWK2YNMVA2I5B4G","bundle":"https://pith.science/pith/WUDNHOJBTFGQWK2YNMVA2I5B4G/bundle.json","state":"https://pith.science/pith/WUDNHOJBTFGQWK2YNMVA2I5B4G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUDNHOJBTFGQWK2YNMVA2I5B4G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WUDNHOJBTFGQWK2YNMVA2I5B4G","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":"ebaccb540f2f6f165eeb03e8a382f67e6f193a84bdd5cdc6661b945c6d306c8d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-26T10:39:03Z","title_canon_sha256":"45df09bdde7e2aac908885862688a22c1e8f1d35e9d851c74bd7d848f870e1a2"},"schema_version":"1.0","source":{"id":"2011.13220","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13220","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13220v1","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13220","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"WUDNHOJBTFGQ","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_16","alias_value":"WUDNHOJBTFGQWK2Y","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_8","alias_value":"WUDNHOJB","created_at":"2026-07-05T01:54:52Z"}],"graph_snapshots":[{"event_id":"sha256:c83224adbc07fb497460d2ef381d79b78f336e2a04156100ae4d1ea429f3ef2e","target":"graph","created_at":"2026-07-05T01:54:52Z","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/2011.13220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Perplexity is a widely used performance metric for language models, the values are highly dependent upon the number of words in the corpus and is useful to compare performance of the same corpus only. In this paper, we propose a new metric that can be used to evaluate language model performance with different vocabulary sizes. The proposed unigram-normalized Perplexity actually presents the performance improvement of the language models from that of simple unigram model, and is robust on the vocabulary size. Both theoretical analysis and computational experiments are reported.","authors_text":"Jihyeon Roh, Sang-Hoon Oh, Soo-Young Lee","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-26T10:39:03Z","title":"Unigram-Normalized Perplexity as a Language Model Performance Measure with Different Vocabulary Sizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13220","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":"sha256:376a66c1fbd887508c11618f6f891a52b1381732cc926db29443a6566be06231","target":"record","created_at":"2026-07-05T01:54:52Z","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":"ebaccb540f2f6f165eeb03e8a382f67e6f193a84bdd5cdc6661b945c6d306c8d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-26T10:39:03Z","title_canon_sha256":"45df09bdde7e2aac908885862688a22c1e8f1d35e9d851c74bd7d848f870e1a2"},"schema_version":"1.0","source":{"id":"2011.13220","kind":"arxiv","version":1}},"canonical_sha256":"b506d3b921994d0b2b586b2a0d23a1e1bcc7110a3fd03950d0bb17f2a8a2428b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b506d3b921994d0b2b586b2a0d23a1e1bcc7110a3fd03950d0bb17f2a8a2428b","first_computed_at":"2026-07-05T01:54:52.093852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:54:52.093852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HVvdiRecrvP06dSsBTchJMcj7jpqsK0GKP2sDbI8dGmzhNwv7e3qRY/rTwtRmcdvNdZmyi/2ZIzAQWcRXsLtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:54:52.094406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.13220","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:376a66c1fbd887508c11618f6f891a52b1381732cc926db29443a6566be06231","sha256:c83224adbc07fb497460d2ef381d79b78f336e2a04156100ae4d1ea429f3ef2e"],"state_sha256":"408f7f2646711e7a44f2f7e376dc18f2ffbda8103c6912ec442b85e4cb13381f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B4DAyFQ79Jl45865yTnxaUdvLFDCKJUXiVX3ArsjyqWIOFDDGBDw847W9h14l9S6kFeIojuSju2++J/VOti0Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:23:01.771948Z","bundle_sha256":"be589f6920c5135060e04698a2940d18d86a1fe0413872ed5cfda0aaedf40ec7"}}