{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SM4ORUDE7EBO7AXIZYM4X5MZT6","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":"89266f8fee5b1c320185de5432e51a2ae8f86f5597f643064a3022f93cea93c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T16:57:32Z","title_canon_sha256":"6b92fe454956edf0b76af701152e555d7b232d6571e34a25dae71f1ee0854078"},"schema_version":"1.0","source":{"id":"2307.15002","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15002","created_at":"2026-07-05T06:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15002v5","created_at":"2026-07-05T06:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15002","created_at":"2026-07-05T06:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"SM4ORUDE7EBO","created_at":"2026-07-05T06:39:05Z"},{"alias_kind":"pith_short_16","alias_value":"SM4ORUDE7EBO7AXI","created_at":"2026-07-05T06:39:05Z"},{"alias_kind":"pith_short_8","alias_value":"SM4ORUDE","created_at":"2026-07-05T06:39:05Z"}],"graph_snapshots":[{"event_id":"sha256:3d123d82cb289477ec144da1d6974ded5ef775037976376e00b0e4afa2788ca7","target":"graph","created_at":"2026-07-05T06:39:05Z","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/2307.15002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The effectiveness of compression in text classification ('gzip') has recently garnered lots of attention. In this note we show that `bag-of-words' approaches can achieve similar or better results, and are more efficient.","authors_text":"Juri Opitz","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T16:57:32Z","title":"Gzip versus bag-of-words for text classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15002","kind":"arxiv","version":5},"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":"sha256:32191ffd9f55ed0546b69555ea95b67c1aff4d0d7c2142ee8f8b9218074ceaae","target":"record","created_at":"2026-07-05T06:39:05Z","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":"89266f8fee5b1c320185de5432e51a2ae8f86f5597f643064a3022f93cea93c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T16:57:32Z","title_canon_sha256":"6b92fe454956edf0b76af701152e555d7b232d6571e34a25dae71f1ee0854078"},"schema_version":"1.0","source":{"id":"2307.15002","kind":"arxiv","version":5}},"canonical_sha256":"9338e8d064f902ef82e8ce19cbf5999f916ac66101c69da564710d7832d28b33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9338e8d064f902ef82e8ce19cbf5999f916ac66101c69da564710d7832d28b33","first_computed_at":"2026-07-05T06:39:05.852771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:05.852771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7AsnKhTBtrl3g+CjsmLl7Cl+WYH0v/KAshfacfOIZvstOxrv1ASS3WJSoOfzZNkZgpEe4IsNjIHXey9NZKpMAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:05.853145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15002","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32191ffd9f55ed0546b69555ea95b67c1aff4d0d7c2142ee8f8b9218074ceaae","sha256:3d123d82cb289477ec144da1d6974ded5ef775037976376e00b0e4afa2788ca7"],"state_sha256":"cc8e923c666fa4a8bdd7ef23cc1fd9f1f7047c9f2b15e8329fbd2a9a4fbd6ace"}