{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:F77MT2DKH7EAEUTGWMSXBSJ3P5","short_pith_number":"pith:F77MT2DK","canonical_record":{"source":{"id":"2003.08529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T00:48:32Z","cross_cats_sorted":[],"title_canon_sha256":"56927921044ba119d75a9d7414692d0955b8245567745a063324a64451a67d12","abstract_canon_sha256":"c690bbee7297fcea97b74097c4a430c54b73582d79ac2331ea6f9a9742f1f3f7"},"schema_version":"1.0"},"canonical_sha256":"2ffec9e86a3fc8025266b32570c93b7f59fbb4e3de89596d180ab7f2c961a62e","source":{"kind":"arxiv","id":"2003.08529","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.08529","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"arxiv_version","alias_value":"2003.08529v1","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08529","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"pith_short_12","alias_value":"F77MT2DKH7EA","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"pith_short_16","alias_value":"F77MT2DKH7EAEUTG","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"pith_short_8","alias_value":"F77MT2DK","created_at":"2026-07-05T00:49:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:F77MT2DKH7EAEUTGWMSXBSJ3P5","target":"record","payload":{"canonical_record":{"source":{"id":"2003.08529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T00:48:32Z","cross_cats_sorted":[],"title_canon_sha256":"56927921044ba119d75a9d7414692d0955b8245567745a063324a64451a67d12","abstract_canon_sha256":"c690bbee7297fcea97b74097c4a430c54b73582d79ac2331ea6f9a9742f1f3f7"},"schema_version":"1.0"},"canonical_sha256":"2ffec9e86a3fc8025266b32570c93b7f59fbb4e3de89596d180ab7f2c961a62e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:11.551571Z","signature_b64":"nyWcfXCSqeZbPeXVX3nCWLmADYjsBdJow3GVnnJwnFL421fVuQRznc73L579A0CsTEPqEcDJvWpAoyu9JIMkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ffec9e86a3fc8025266b32570c93b7f59fbb4e3de89596d180ab7f2c961a62e","last_reissued_at":"2026-07-05T00:49:11.551125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:11.551125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.08529","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":"2026-07-05T00:49:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6irYjeRqiS4S2KklsHghFAFefQVLurmGgNpCLWEmytwz3zXwcD3JGdbry5w8+C/dUm3XLnFCxCMf5EjhT9aCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:53.793596Z"},"content_sha256":"216806f25a38f5aec7c2b5d008217c0f8c0b8e46ebc42ff9a67a2c08362ba114","schema_version":"1.0","event_id":"sha256:216806f25a38f5aec7c2b5d008217c0f8c0b8e46ebc42ff9a67a2c08362ba114"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:F77MT2DKH7EAEUTGWMSXBSJ3P5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mona Diab, Xuan Zhu, Yi-An Lai, Yi Zhang","submitted_at":"2020-03-19T00:48:32Z","abstract_excerpt":"Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point. However, as natural language processing methods flourish, there are still insufficient characteristic metrics to describe a collection of texts in terms of the words, sentences, or paragraphs they comprise. In this work, we propose metrics of diversity, density, and homogeneity that quantitatively measure the dispersion, sparsity, and uniformity of a text collection. We conduct a series of simulations to verify that each metric holds desired properties and resonates with hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08529","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/2003.08529/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":"2026-07-05T00:49:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"44XPL37MgOr6AiW2L4fQds0HU23m44B41Kc7jgsQS0yaRRGvNog+YS9qPlBPGHSvkjU8n3FE938D9oyx570MCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:53.794095Z"},"content_sha256":"9f30a72a096ee533e9ae47e41aee32e4bcdd74ec1d9c6b8d05f6aa2d7c39750b","schema_version":"1.0","event_id":"sha256:9f30a72a096ee533e9ae47e41aee32e4bcdd74ec1d9c6b8d05f6aa2d7c39750b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F77MT2DKH7EAEUTGWMSXBSJ3P5/bundle.json","state_url":"https://pith.science/pith/F77MT2DKH7EAEUTGWMSXBSJ3P5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F77MT2DKH7EAEUTGWMSXBSJ3P5/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":"2026-08-08T13:15:53Z","links":{"resolver":"https://pith.science/pith/F77MT2DKH7EAEUTGWMSXBSJ3P5","bundle":"https://pith.science/pith/F77MT2DKH7EAEUTGWMSXBSJ3P5/bundle.json","state":"https://pith.science/pith/F77MT2DKH7EAEUTGWMSXBSJ3P5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F77MT2DKH7EAEUTGWMSXBSJ3P5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:F77MT2DKH7EAEUTGWMSXBSJ3P5","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":"c690bbee7297fcea97b74097c4a430c54b73582d79ac2331ea6f9a9742f1f3f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T00:48:32Z","title_canon_sha256":"56927921044ba119d75a9d7414692d0955b8245567745a063324a64451a67d12"},"schema_version":"1.0","source":{"id":"2003.08529","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.08529","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"arxiv_version","alias_value":"2003.08529v1","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08529","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"pith_short_12","alias_value":"F77MT2DKH7EA","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"pith_short_16","alias_value":"F77MT2DKH7EAEUTG","created_at":"2026-07-05T00:49:11Z"},{"alias_kind":"pith_short_8","alias_value":"F77MT2DK","created_at":"2026-07-05T00:49:11Z"}],"graph_snapshots":[{"event_id":"sha256:9f30a72a096ee533e9ae47e41aee32e4bcdd74ec1d9c6b8d05f6aa2d7c39750b","target":"graph","created_at":"2026-07-05T00:49:11Z","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/2003.08529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point. However, as natural language processing methods flourish, there are still insufficient characteristic metrics to describe a collection of texts in terms of the words, sentences, or paragraphs they comprise. In this work, we propose metrics of diversity, density, and homogeneity that quantitatively measure the dispersion, sparsity, and uniformity of a text collection. We conduct a series of simulations to verify that each metric holds desired properties and resonates with hum","authors_text":"Mona Diab, Xuan Zhu, Yi-An Lai, Yi Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T00:48:32Z","title":"Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08529","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":"sha256:216806f25a38f5aec7c2b5d008217c0f8c0b8e46ebc42ff9a67a2c08362ba114","target":"record","created_at":"2026-07-05T00:49:11Z","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":"c690bbee7297fcea97b74097c4a430c54b73582d79ac2331ea6f9a9742f1f3f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T00:48:32Z","title_canon_sha256":"56927921044ba119d75a9d7414692d0955b8245567745a063324a64451a67d12"},"schema_version":"1.0","source":{"id":"2003.08529","kind":"arxiv","version":1}},"canonical_sha256":"2ffec9e86a3fc8025266b32570c93b7f59fbb4e3de89596d180ab7f2c961a62e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ffec9e86a3fc8025266b32570c93b7f59fbb4e3de89596d180ab7f2c961a62e","first_computed_at":"2026-07-05T00:49:11.551125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:49:11.551125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nyWcfXCSqeZbPeXVX3nCWLmADYjsBdJow3GVnnJwnFL421fVuQRznc73L579A0CsTEPqEcDJvWpAoyu9JIMkBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:49:11.551571Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.08529","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:216806f25a38f5aec7c2b5d008217c0f8c0b8e46ebc42ff9a67a2c08362ba114","sha256:9f30a72a096ee533e9ae47e41aee32e4bcdd74ec1d9c6b8d05f6aa2d7c39750b"],"state_sha256":"5aef2d84c89992023cfa75a5a269a2605e1a362999cff2b4c264b17087bdf6f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7An60/hLPG/Q8u0Msw3xUKrofvVq4wodOPIySaRaq9lV/nesoLhSLTmkOfcTbHCO2wvbwb76qsaQJMOEw1mzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:15:53.797630Z","bundle_sha256":"a189ce12ab9afbacefc1a52a2ef22522f23a2bace73d84abfcb01b7621ee7797"}}