{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H2WYXHAUIDQ27HKD7SQKL4RZW7","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":"2010ca7abc82e110fb90a88ff7035ef37b8ede829f17d959ce8711cb60455801","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2023-10-27T08:51:19Z","title_canon_sha256":"a6a3ccb23820055a2ec103c337dc7cc5792200eaa2f225646c0620163918e23d"},"schema_version":"1.0","source":{"id":"2310.17980","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17980","created_at":"2026-07-05T08:56:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17980v3","created_at":"2026-07-05T08:56:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17980","created_at":"2026-07-05T08:56:14Z"},{"alias_kind":"pith_short_12","alias_value":"H2WYXHAUIDQ2","created_at":"2026-07-05T08:56:14Z"},{"alias_kind":"pith_short_16","alias_value":"H2WYXHAUIDQ27HKD","created_at":"2026-07-05T08:56:14Z"},{"alias_kind":"pith_short_8","alias_value":"H2WYXHAU","created_at":"2026-07-05T08:56:14Z"}],"graph_snapshots":[{"event_id":"sha256:a32db2f450baa67b9365d8d02d3efbb8e0f266e2180e2db2411f42fb8a436b90","target":"graph","created_at":"2026-07-05T08:56:14Z","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/2310.17980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We initiate the study of sub-linear sketching and streaming techniques for estimating the output size of common dictionary compressors such as Lempel-Ziv '77, the run-length Burrows-Wheeler transform, and grammar compression. To this end, we focus on a measure that has recently gained much attention in the information-theoretic community and which approximates up to a polylogarithmic multiplicative factor the output sizes of those compressors: the normalized substring complexity function $\\delta$.\n  We present a data sketch of $O(\\epsilon^{-3}\\log n + \\epsilon^{-1}\\log^2 n)$ words that allows ","authors_text":"Bojana Kodric, Davide Cenzato, Matteo Canton, Nicola Prezza, Ruben Becker, Sung-Hwan Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2023-10-27T08:51:19Z","title":"Sketching and Streaming for Dictionary Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17980","kind":"arxiv","version":3},"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:a71a6bcbb91e1c8e46ba35b4766651eefc32af41be23f524827843067aea45b6","target":"record","created_at":"2026-07-05T08:56:14Z","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":"2010ca7abc82e110fb90a88ff7035ef37b8ede829f17d959ce8711cb60455801","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2023-10-27T08:51:19Z","title_canon_sha256":"a6a3ccb23820055a2ec103c337dc7cc5792200eaa2f225646c0620163918e23d"},"schema_version":"1.0","source":{"id":"2310.17980","kind":"arxiv","version":3}},"canonical_sha256":"3ead8b9c1440e1af9d43fca0a5f239b7fcf41250586afeb2e88276a50ec4a454","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ead8b9c1440e1af9d43fca0a5f239b7fcf41250586afeb2e88276a50ec4a454","first_computed_at":"2026-07-05T08:56:14.836523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:14.836523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cynZESBnsN99u7yAXAmSXZ6mJ7PVsGy4yDuVgObscXDZg7Hyg/SQiDOvVwHH1Zqmz10VJCqqxKrxQFoQgm3RDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:14.836925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17980","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a71a6bcbb91e1c8e46ba35b4766651eefc32af41be23f524827843067aea45b6","sha256:a32db2f450baa67b9365d8d02d3efbb8e0f266e2180e2db2411f42fb8a436b90"],"state_sha256":"3ea6d96436ab01895c6bdf33a028f1454119719f60bea2fdd2eefae6e9467fda"}