{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2002:MMNG3B5VQ5KV54X2EH2A2AJJ4X","short_pith_number":"pith:MMNG3B5V","schema_version":"1.0","canonical_sha256":"631a6d87b587555ef2fa21f40d0129e5d0c6c0154919671bb8484538abab4d1f","source":{"kind":"arxiv","id":"cs/0205029","version":1},"attestation_state":"computed","paper":{"title":"A Codebook Generation Algorithm for Document Image Compression","license":"","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"John Danskin, Neal Young, Qin Zhang","submitted_at":"2002-05-17T23:52:11Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"cs/0205029","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.DS","submitted_at":"2002-05-17T23:52:11Z","cross_cats_sorted":[],"title_canon_sha256":"f8f33af23d361a563f65947901a35eeceec827e9a4e93aa2b8a6fe0ecf95b09c","abstract_canon_sha256":"c703c2da724f4fe9da78a9773a9dae9082e4f845cf1197aa65ee7c2d5c92ece7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:44.403337Z","signature_b64":"CkMlCBvUtGIN/BtRLg1nrIPV6Fy5L8ibxKFUUWrxt2FGKTY+QSDdL1QCeRmlWPc7GTKq9CtPeSZIO+vtfcGgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631a6d87b587555ef2fa21f40d0129e5d0c6c0154919671bb8484538abab4d1f","last_reissued_at":"2026-05-18T01:22:44.402692Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:44.402692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Codebook Generation Algorithm for Document Image Compression","license":"","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"John Danskin, Neal Young, Qin Zhang","submitted_at":"2002-05-17T23:52:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0205029","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"cs/0205029","created_at":"2026-05-18T01:22:44.402793+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0205029v1","created_at":"2026-05-18T01:22:44.402793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0205029","created_at":"2026-05-18T01:22:44.402793+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMNG3B5VQ5KV","created_at":"2026-05-18T12:25:51.375804+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMNG3B5VQ5KV54X2","created_at":"2026-05-18T12:25:51.375804+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMNG3B5V","created_at":"2026-05-18T12:25:51.375804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X","json":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X.json","graph_json":"https://pith.science/api/pith-number/MMNG3B5VQ5KV54X2EH2A2AJJ4X/graph.json","events_json":"https://pith.science/api/pith-number/MMNG3B5VQ5KV54X2EH2A2AJJ4X/events.json","paper":"https://pith.science/paper/MMNG3B5V"},"agent_actions":{"view_html":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X","download_json":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X.json","view_paper":"https://pith.science/paper/MMNG3B5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0205029&json=true","fetch_graph":"https://pith.science/api/pith-number/MMNG3B5VQ5KV54X2EH2A2AJJ4X/graph.json","fetch_events":"https://pith.science/api/pith-number/MMNG3B5VQ5KV54X2EH2A2AJJ4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X/action/storage_attestation","attest_author":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X/action/author_attestation","sign_citation":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X/action/citation_signature","submit_replication":"https://pith.science/pith/MMNG3B5VQ5KV54X2EH2A2AJJ4X/action/replication_record"}},"created_at":"2026-05-18T01:22:44.402793+00:00","updated_at":"2026-05-18T01:22:44.402793+00:00"}