{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:X4YAAEDJOTWN7GMQUYO6PM2GPH","short_pith_number":"pith:X4YAAEDJ","canonical_record":{"source":{"id":"1601.07969","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-29T02:39:56Z","cross_cats_sorted":[],"title_canon_sha256":"0aeb7246b156afbfd6490187eb49ef60903e4e8f00022f7bb9630228e0f7141d","abstract_canon_sha256":"770f77b5d20df5d6d688b1250188e270bb810ece355708b61ec1d00a7224c46c"},"schema_version":"1.0"},"canonical_sha256":"bf3000106974ecdf9990a61de7b34679d852cdb3f8954187dc324f0166d02298","source":{"kind":"arxiv","id":"1601.07969","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.07969","created_at":"2026-05-18T01:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"1601.07969v2","created_at":"2026-05-18T01:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.07969","created_at":"2026-05-18T01:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"X4YAAEDJOTWN","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"X4YAAEDJOTWN7GMQ","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"X4YAAEDJ","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:X4YAAEDJOTWN7GMQUYO6PM2GPH","target":"record","payload":{"canonical_record":{"source":{"id":"1601.07969","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-29T02:39:56Z","cross_cats_sorted":[],"title_canon_sha256":"0aeb7246b156afbfd6490187eb49ef60903e4e8f00022f7bb9630228e0f7141d","abstract_canon_sha256":"770f77b5d20df5d6d688b1250188e270bb810ece355708b61ec1d00a7224c46c"},"schema_version":"1.0"},"canonical_sha256":"bf3000106974ecdf9990a61de7b34679d852cdb3f8954187dc324f0166d02298","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:41.818877Z","signature_b64":"xx3DWMhP8JnrZWi/Jvy5e9pJGNz8J+HstMSp71+JBuscZIdp8ZyeyCBZytpnxd4rmynRRK2piyHm5m6HAwsADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3000106974ecdf9990a61de7b34679d852cdb3f8954187dc324f0166d02298","last_reissued_at":"2026-05-18T01:09:41.818336Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:41.818336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1601.07969","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oiY8wCavBm/K4RD67FKn1Pd0165AfFkoU34z41nsNk0bK40OTZDylYFoInqaXdUyb7O7KlTKPC8uX2AClFuWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:48:24.912370Z"},"content_sha256":"987bb65808a06044e5f5f08a70cee871601f11082c2298773cecb376593599eb","schema_version":"1.0","event_id":"sha256:987bb65808a06044e5f5f08a70cee871601f11082c2298773cecb376593599eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:X4YAAEDJOTWN7GMQUYO6PM2GPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zipf's law is a consequence of coherent language production","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew J. Reagan, Christopher M. Danforth, Jake Ryland Williams, James P. Bagrow, Peter Sheridan Dodds, Sharon E. Alajajian","submitted_at":"2016-01-29T02:39:56Z","abstract_excerpt":"The task of text segmentation may be undertaken at many levels in text analysis---paragraphs, sentences, words, or even letters. Here, we focus on a relatively fine scale of segmentation, hypothesizing it to be in accord with a stochastic model of language generation, as the smallest scale where independent units of meaning are produced. Our goals in this letter include the development of methods for the segmentation of these minimal independent units, which produce feature-representations of texts that align with the independence assumption of the bag-of-terms model, commonly used for predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.07969","kind":"arxiv","version":2},"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":"2026-05-18T01:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wIWnc+LdZwDBzWurQNDzBZSVCjwXiSNa0YSDJebhG57OksTmf0zU1IMXdWkvWlmrxiaZLV7fPs5JFFl5Vpl5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:48:24.912720Z"},"content_sha256":"e93e40e6790a63db69710005d0d91e77d9aa8181cc12a2ba5a3700a48317ae58","schema_version":"1.0","event_id":"sha256:e93e40e6790a63db69710005d0d91e77d9aa8181cc12a2ba5a3700a48317ae58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4YAAEDJOTWN7GMQUYO6PM2GPH/bundle.json","state_url":"https://pith.science/pith/X4YAAEDJOTWN7GMQUYO6PM2GPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4YAAEDJOTWN7GMQUYO6PM2GPH/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":"2026-05-28T18:48:24Z","links":{"resolver":"https://pith.science/pith/X4YAAEDJOTWN7GMQUYO6PM2GPH","bundle":"https://pith.science/pith/X4YAAEDJOTWN7GMQUYO6PM2GPH/bundle.json","state":"https://pith.science/pith/X4YAAEDJOTWN7GMQUYO6PM2GPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4YAAEDJOTWN7GMQUYO6PM2GPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:X4YAAEDJOTWN7GMQUYO6PM2GPH","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":"770f77b5d20df5d6d688b1250188e270bb810ece355708b61ec1d00a7224c46c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-29T02:39:56Z","title_canon_sha256":"0aeb7246b156afbfd6490187eb49ef60903e4e8f00022f7bb9630228e0f7141d"},"schema_version":"1.0","source":{"id":"1601.07969","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.07969","created_at":"2026-05-18T01:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"1601.07969v2","created_at":"2026-05-18T01:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.07969","created_at":"2026-05-18T01:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"X4YAAEDJOTWN","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"X4YAAEDJOTWN7GMQ","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"X4YAAEDJ","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:e93e40e6790a63db69710005d0d91e77d9aa8181cc12a2ba5a3700a48317ae58","target":"graph","created_at":"2026-05-18T01:09:41Z","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 task of text segmentation may be undertaken at many levels in text analysis---paragraphs, sentences, words, or even letters. Here, we focus on a relatively fine scale of segmentation, hypothesizing it to be in accord with a stochastic model of language generation, as the smallest scale where independent units of meaning are produced. Our goals in this letter include the development of methods for the segmentation of these minimal independent units, which produce feature-representations of texts that align with the independence assumption of the bag-of-terms model, commonly used for predict","authors_text":"Andrew J. Reagan, Christopher M. Danforth, Jake Ryland Williams, James P. Bagrow, Peter Sheridan Dodds, Sharon E. Alajajian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-29T02:39:56Z","title":"Zipf's law is a consequence of coherent language production"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.07969","kind":"arxiv","version":2},"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":"sha256:987bb65808a06044e5f5f08a70cee871601f11082c2298773cecb376593599eb","target":"record","created_at":"2026-05-18T01:09:41Z","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":"770f77b5d20df5d6d688b1250188e270bb810ece355708b61ec1d00a7224c46c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-29T02:39:56Z","title_canon_sha256":"0aeb7246b156afbfd6490187eb49ef60903e4e8f00022f7bb9630228e0f7141d"},"schema_version":"1.0","source":{"id":"1601.07969","kind":"arxiv","version":2}},"canonical_sha256":"bf3000106974ecdf9990a61de7b34679d852cdb3f8954187dc324f0166d02298","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf3000106974ecdf9990a61de7b34679d852cdb3f8954187dc324f0166d02298","first_computed_at":"2026-05-18T01:09:41.818336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:09:41.818336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xx3DWMhP8JnrZWi/Jvy5e9pJGNz8J+HstMSp71+JBuscZIdp8ZyeyCBZytpnxd4rmynRRK2piyHm5m6HAwsADA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:09:41.818877Z","signed_message":"canonical_sha256_bytes"},"source_id":"1601.07969","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:987bb65808a06044e5f5f08a70cee871601f11082c2298773cecb376593599eb","sha256:e93e40e6790a63db69710005d0d91e77d9aa8181cc12a2ba5a3700a48317ae58"],"state_sha256":"39327e2467f016256da160f4f3ea2a6eb9138f703a227186b0c8646aa2e323d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IIjyswFGmjfAuTeEQtbUSLHeUrsMLBJdUOAyqm0+jeCh8yGW8q3+hcUJjszvrbemtiYgK8Yt0ikEZdewBcCHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:48:24.915015Z","bundle_sha256":"d301b02d78dedc8a88f1827bc0360cbae403dae544093b36a5d5df4b4bfe125e"}}