{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2002:MMNG3B5VQ5KV54X2EH2A2AJJ4X","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":"c703c2da724f4fe9da78a9773a9dae9082e4f845cf1197aa65ee7c2d5c92ece7","cross_cats_sorted":[],"license":"","primary_cat":"cs.DS","submitted_at":"2002-05-17T23:52:11Z","title_canon_sha256":"f8f33af23d361a563f65947901a35eeceec827e9a4e93aa2b8a6fe0ecf95b09c"},"schema_version":"1.0","source":{"id":"cs/0205029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0205029","created_at":"2026-05-18T01:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0205029v1","created_at":"2026-05-18T01:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0205029","created_at":"2026-05-18T01:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"MMNG3B5VQ5KV","created_at":"2026-05-18T12:25:51Z"},{"alias_kind":"pith_short_16","alias_value":"MMNG3B5VQ5KV54X2","created_at":"2026-05-18T12:25:51Z"},{"alias_kind":"pith_short_8","alias_value":"MMNG3B5V","created_at":"2026-05-18T12:25:51Z"}],"graph_snapshots":[{"event_id":"sha256:d2b52b1249e4605ef8a9147c21a7a7aa8c7ad31ecb686bf1b8bfac2acc39ca99","target":"graph","created_at":"2026-05-18T01:22:44Z","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":"Pattern-matching-based document-compression systems (e.g. for faxing) rely on finding a small set of patterns that can be used to represent all of the ink in the document. Finding an optimal set of patterns is NP-hard; previous compression schemes have resorted to heuristics. This paper describes an extension of the cross-entropy approach, used previously for measuring pattern similarity, to this problem. This approach reduces the problem to a k-medians problem, for which the paper gives a new algorithm with a provably good performance guarantee. In comparison to previous heuristics (First Fit","authors_text":"John Danskin, Neal Young, Qin Zhang","cross_cats":[],"headline":"","license":"","primary_cat":"cs.DS","submitted_at":"2002-05-17T23:52:11Z","title":"A Codebook Generation Algorithm for Document Image Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0205029","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":"sha256:239ced0da6ac8ce961cc031b88fe4493947df589254e7bd49496a4b03c8fcfdb","target":"record","created_at":"2026-05-18T01:22:44Z","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":"c703c2da724f4fe9da78a9773a9dae9082e4f845cf1197aa65ee7c2d5c92ece7","cross_cats_sorted":[],"license":"","primary_cat":"cs.DS","submitted_at":"2002-05-17T23:52:11Z","title_canon_sha256":"f8f33af23d361a563f65947901a35eeceec827e9a4e93aa2b8a6fe0ecf95b09c"},"schema_version":"1.0","source":{"id":"cs/0205029","kind":"arxiv","version":1}},"canonical_sha256":"631a6d87b587555ef2fa21f40d0129e5d0c6c0154919671bb8484538abab4d1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"631a6d87b587555ef2fa21f40d0129e5d0c6c0154919671bb8484538abab4d1f","first_computed_at":"2026-05-18T01:22:44.402692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:22:44.402692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CkMlCBvUtGIN/BtRLg1nrIPV6Fy5L8ibxKFUUWrxt2FGKTY+QSDdL1QCeRmlWPc7GTKq9CtPeSZIO+vtfcGgDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:22:44.403337Z","signed_message":"canonical_sha256_bytes"},"source_id":"cs/0205029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:239ced0da6ac8ce961cc031b88fe4493947df589254e7bd49496a4b03c8fcfdb","sha256:d2b52b1249e4605ef8a9147c21a7a7aa8c7ad31ecb686bf1b8bfac2acc39ca99"],"state_sha256":"b2ae9b539b53eda0412f7e38f015abeb30af12064b36dfb31aac74dcd4488221"}