{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LDK6WK3OMPLW2PCMRQ7AVS75YR","short_pith_number":"pith:LDK6WK3O","schema_version":"1.0","canonical_sha256":"58d5eb2b6e63d76d3c4c8c3e0acbfdc45e1c8725b751859330938f6425fb237b","source":{"kind":"arxiv","id":"1511.06606","version":5},"attestation_state":"computed","paper":{"title":"Data Representation and Compression Using Linear-Programming Approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hristo S. Paskov, John C. Mitchell, Trevor J. Hastie","submitted_at":"2015-11-20T14:21:44Z","abstract_excerpt":"We propose `Dracula', a new framework for unsupervised feature selection from sequential data such as text. Dracula learns a dictionary of $n$-grams that efficiently compresses a given corpus and recursively compresses its own dictionary; in effect, Dracula is a `deep' extension of Compressive Feature Learning. It requires solving a binary linear program that may be relaxed to a linear program. Both problems exhibit considerable structure, their solution paths are well behaved, and we identify parameters which control the depth and diversity of the dictionary. We also discuss how to derive fea"},"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":"1511.06606","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T14:21:44Z","cross_cats_sorted":[],"title_canon_sha256":"9eff0d41b31eded12deaff0864cb07fbd2869669d0b1341636f803a7c4569468","abstract_canon_sha256":"149b0dbee54d9d1e1d16ce2ed8b5cafa92c5912b0a136e5dd9b639abf4665c98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:51.944581Z","signature_b64":"wwbFdTCiOPyCPf9bYGPA9t7bcLEcH4blFvDYI3sX3uNvRSBx2SIPRB0OXW/dImFzSy4+rWxVryyOjbsDPn9lDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58d5eb2b6e63d76d3c4c8c3e0acbfdc45e1c8725b751859330938f6425fb237b","last_reissued_at":"2026-05-18T01:15:51.943998Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:51.943998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Representation and Compression Using Linear-Programming Approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hristo S. Paskov, John C. Mitchell, Trevor J. Hastie","submitted_at":"2015-11-20T14:21:44Z","abstract_excerpt":"We propose `Dracula', a new framework for unsupervised feature selection from sequential data such as text. Dracula learns a dictionary of $n$-grams that efficiently compresses a given corpus and recursively compresses its own dictionary; in effect, Dracula is a `deep' extension of Compressive Feature Learning. It requires solving a binary linear program that may be relaxed to a linear program. Both problems exhibit considerable structure, their solution paths are well behaved, and we identify parameters which control the depth and diversity of the dictionary. We also discuss how to derive fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06606","kind":"arxiv","version":5},"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":"1511.06606","created_at":"2026-05-18T01:15:51.944066+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06606v5","created_at":"2026-05-18T01:15:51.944066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06606","created_at":"2026-05-18T01:15:51.944066+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDK6WK3OMPLW","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDK6WK3OMPLW2PCM","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDK6WK3O","created_at":"2026-05-18T12:29:29.992203+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/LDK6WK3OMPLW2PCMRQ7AVS75YR","json":"https://pith.science/pith/LDK6WK3OMPLW2PCMRQ7AVS75YR.json","graph_json":"https://pith.science/api/pith-number/LDK6WK3OMPLW2PCMRQ7AVS75YR/graph.json","events_json":"https://pith.science/api/pith-number/LDK6WK3OMPLW2PCMRQ7AVS75YR/events.json","paper":"https://pith.science/paper/LDK6WK3O"},"agent_actions":{"view_html":"https://pith.science/pith/LDK6WK3OMPLW2PCMRQ7AVS75YR","download_json":"https://pith.science/pith/LDK6WK3OMPLW2PCMRQ7AVS75YR.json","view_paper":"https://pith.science/paper/LDK6WK3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06606&json=true","fetch_graph":"https://pith.science/api/pith-number/LDK6WK3OMPLW2PCMRQ7AVS75YR/graph.json","fetch_events":"https://pith.science/api/pith-number/LDK6WK3OMPLW2PCMRQ7AVS75YR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDK6WK3OMPLW2PCMRQ7AVS75YR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDK6WK3OMPLW2PCMRQ7AVS75YR/action/storage_attestation","attest_author":"https://pith.science/pith/LDK6WK3OMPLW2PCMRQ7AVS75YR/action/author_attestation","sign_citation":"https://pith.science/pith/LDK6WK3OMPLW2PCMRQ7AVS75YR/action/citation_signature","submit_replication":"https://pith.science/pith/LDK6WK3OMPLW2PCMRQ7AVS75YR/action/replication_record"}},"created_at":"2026-05-18T01:15:51.944066+00:00","updated_at":"2026-05-18T01:15:51.944066+00:00"}