{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VSU7VYZITRFVBRGL2MHHJGKMBC","short_pith_number":"pith:VSU7VYZI","canonical_record":{"source":{"id":"2507.15092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T19:14:43Z","cross_cats_sorted":[],"title_canon_sha256":"0f67c921096ce98ea96e4603e367d96a1aaae0cdbd0c9434bdd48ed3d94c7033","abstract_canon_sha256":"173af00a902ace52705de306f3356027f4222d6311fc867a68bb04da2e8b59ad"},"schema_version":"1.0"},"canonical_sha256":"aca9fae3289c4b50c4cbd30e74994c0888584b3f5bbbc03108bd65027afe9a61","source":{"kind":"arxiv","id":"2507.15092","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15092","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15092v1","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15092","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"VSU7VYZITRFV","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_16","alias_value":"VSU7VYZITRFVBRGL","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_8","alias_value":"VSU7VYZI","created_at":"2026-07-05T11:40:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VSU7VYZITRFVBRGL2MHHJGKMBC","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T19:14:43Z","cross_cats_sorted":[],"title_canon_sha256":"0f67c921096ce98ea96e4603e367d96a1aaae0cdbd0c9434bdd48ed3d94c7033","abstract_canon_sha256":"173af00a902ace52705de306f3356027f4222d6311fc867a68bb04da2e8b59ad"},"schema_version":"1.0"},"canonical_sha256":"aca9fae3289c4b50c4cbd30e74994c0888584b3f5bbbc03108bd65027afe9a61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:18.401010Z","signature_b64":"48/ocIUPfL4K1mY2FmLcfdY6kCJPSi7OjsnWHBH02cDCXMgucsS2NIwQvuxdbEjLlCNAK7el4dVXqcxpucVbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aca9fae3289c4b50c4cbd30e74994c0888584b3f5bbbc03108bd65027afe9a61","last_reissued_at":"2026-07-05T11:40:18.400400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:18.400400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15092","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":"2026-07-05T11:40:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i52iVsDEh30FA3DP3MtmfvKMxMrLU30ePq5WKEQwmH9B+Xd1sTOCpowKJx3TZYOgJEdSZ7cgZRp567XBJ0nMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:52:38.875699Z"},"content_sha256":"53a525405567759f278f289ba8355a24422095d9c8939f285a57bed5b2f997ed","schema_version":"1.0","event_id":"sha256:53a525405567759f278f289ba8355a24422095d9c8939f285a57bed5b2f997ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VSU7VYZITRFVBRGL2MHHJGKMBC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Rumshisky, Ishita Dasgupta, Saayan Mitra, Somdeb Sarkhel, Uttaran Bhattacharya, Vijeta Deshpande","submitted_at":"2025-07-20T19:14:43Z","abstract_excerpt":"Synthetic text generated by Large Language Models (LLMs) is increasingly used for further training and improvement of LLMs. Diversity is crucial for the effectiveness of synthetic data, and researchers rely on prompt engineering to improve diversity. However, the impact of prompt variations on response text length, and, more importantly, the consequential effect on lexical diversity measurements, remain underexplored. In this work, we propose Penalty-Adjusted Type-Token Ratio (PATTR), a diversity metric robust to length variations. We generate a large synthetic corpus of over 20M words using s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15092","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/2507.15092/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":"2026-07-05T11:40:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fajNeIycd1X7988MaUbV8eEn1Pk+QHyCpAHj+M9CEmI5aYlSRMETX2XDPFsT/e9JvtpomZeImtFwF+7gtiM0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:52:38.876230Z"},"content_sha256":"a8665d7ce575c4146bdd7b22944180b9a6c643480f7cc7323e11d7c9b1baedbc","schema_version":"1.0","event_id":"sha256:a8665d7ce575c4146bdd7b22944180b9a6c643480f7cc7323e11d7c9b1baedbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSU7VYZITRFVBRGL2MHHJGKMBC/bundle.json","state_url":"https://pith.science/pith/VSU7VYZITRFVBRGL2MHHJGKMBC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSU7VYZITRFVBRGL2MHHJGKMBC/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":"2026-08-04T16:52:38Z","links":{"resolver":"https://pith.science/pith/VSU7VYZITRFVBRGL2MHHJGKMBC","bundle":"https://pith.science/pith/VSU7VYZITRFVBRGL2MHHJGKMBC/bundle.json","state":"https://pith.science/pith/VSU7VYZITRFVBRGL2MHHJGKMBC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSU7VYZITRFVBRGL2MHHJGKMBC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VSU7VYZITRFVBRGL2MHHJGKMBC","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":"173af00a902ace52705de306f3356027f4222d6311fc867a68bb04da2e8b59ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T19:14:43Z","title_canon_sha256":"0f67c921096ce98ea96e4603e367d96a1aaae0cdbd0c9434bdd48ed3d94c7033"},"schema_version":"1.0","source":{"id":"2507.15092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15092","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15092v1","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15092","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"VSU7VYZITRFV","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_16","alias_value":"VSU7VYZITRFVBRGL","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_8","alias_value":"VSU7VYZI","created_at":"2026-07-05T11:40:18Z"}],"graph_snapshots":[{"event_id":"sha256:a8665d7ce575c4146bdd7b22944180b9a6c643480f7cc7323e11d7c9b1baedbc","target":"graph","created_at":"2026-07-05T11:40:18Z","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/2507.15092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic text generated by Large Language Models (LLMs) is increasingly used for further training and improvement of LLMs. Diversity is crucial for the effectiveness of synthetic data, and researchers rely on prompt engineering to improve diversity. However, the impact of prompt variations on response text length, and, more importantly, the consequential effect on lexical diversity measurements, remain underexplored. In this work, we propose Penalty-Adjusted Type-Token Ratio (PATTR), a diversity metric robust to length variations. We generate a large synthetic corpus of over 20M words using s","authors_text":"Anna Rumshisky, Ishita Dasgupta, Saayan Mitra, Somdeb Sarkhel, Uttaran Bhattacharya, Vijeta Deshpande","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T19:14:43Z","title":"A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15092","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":"sha256:53a525405567759f278f289ba8355a24422095d9c8939f285a57bed5b2f997ed","target":"record","created_at":"2026-07-05T11:40:18Z","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":"173af00a902ace52705de306f3356027f4222d6311fc867a68bb04da2e8b59ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T19:14:43Z","title_canon_sha256":"0f67c921096ce98ea96e4603e367d96a1aaae0cdbd0c9434bdd48ed3d94c7033"},"schema_version":"1.0","source":{"id":"2507.15092","kind":"arxiv","version":1}},"canonical_sha256":"aca9fae3289c4b50c4cbd30e74994c0888584b3f5bbbc03108bd65027afe9a61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aca9fae3289c4b50c4cbd30e74994c0888584b3f5bbbc03108bd65027afe9a61","first_computed_at":"2026-07-05T11:40:18.400400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:18.400400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"48/ocIUPfL4K1mY2FmLcfdY6kCJPSi7OjsnWHBH02cDCXMgucsS2NIwQvuxdbEjLlCNAK7el4dVXqcxpucVbDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:18.401010Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53a525405567759f278f289ba8355a24422095d9c8939f285a57bed5b2f997ed","sha256:a8665d7ce575c4146bdd7b22944180b9a6c643480f7cc7323e11d7c9b1baedbc"],"state_sha256":"452ce1c854c95b4169d45a4628c94cf1d48e7af0c2e3a0fc4534cdd375f01bc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"talMu7bKtGKPVY1087AGQdzX3l7G+JauwBhd5vxGmnr9b9FDfhsHDeuuBPdxZJ1K3jAKqgmhyRnSg59dxz5DCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:52:38.879599Z","bundle_sha256":"57da8252d0697e7e6931f239c7f9b2e0d55cf8bc86f7bdc002701e53f485d603"}}