{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:2ZD6GEPSTOVGMWS3JGDRDVMAKL","short_pith_number":"pith:2ZD6GEPS","schema_version":"1.0","canonical_sha256":"d647e311f29baa665a5b498711d58052c4defc1fbdc9ff74fe209235f63f3ef3","source":{"kind":"arxiv","id":"1108.1956","version":1},"attestation_state":"computed","paper":{"title":"Factorization-based Lossless Compression of Inverted Indices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"George Beskales, Marcus Fontoura, Maxim Gurevich, Sergei Vassilvitskii, Vanja Josifovski","submitted_at":"2011-08-09T15:25:17Z","abstract_excerpt":"Many large-scale Web applications that require ranked top-k retrieval such as Web search and online advertising are implemented using inverted indices. An inverted index represents a sparse term-document matrix, where non-zero elements indicate the strength of term-document association. In this work, we present an approach for lossless compression of inverted indices. Our approach maps terms in a document corpus to a new term space in order to reduce the number of non-zero elements in the term-document matrix, resulting in a more compact inverted index. We formulate the problem of selecting a "},"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":"1108.1956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2011-08-09T15:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"f30676f0ae89b771023c4640a69d45b1f35b1cf3e6449b6d0a08f33536c910c6","abstract_canon_sha256":"56fd7f5b34a06ea5d53908ccac4e89ba46072475e4483311b3d4275fce980e91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:42.358023Z","signature_b64":"jGLR3W+7ryR5lqKO4t+vRXRElTpBNfETj3c3UYlh+hV5tDNK5XV3tB0oQZXMNJb43wPZk84vnEse4oR7T7VxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d647e311f29baa665a5b498711d58052c4defc1fbdc9ff74fe209235f63f3ef3","last_reissued_at":"2026-05-18T02:21:42.357579Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:42.357579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factorization-based Lossless Compression of Inverted Indices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"George Beskales, Marcus Fontoura, Maxim Gurevich, Sergei Vassilvitskii, Vanja Josifovski","submitted_at":"2011-08-09T15:25:17Z","abstract_excerpt":"Many large-scale Web applications that require ranked top-k retrieval such as Web search and online advertising are implemented using inverted indices. An inverted index represents a sparse term-document matrix, where non-zero elements indicate the strength of term-document association. In this work, we present an approach for lossless compression of inverted indices. Our approach maps terms in a document corpus to a new term space in order to reduce the number of non-zero elements in the term-document matrix, resulting in a more compact inverted index. We formulate the problem of selecting a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.1956","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":"1108.1956","created_at":"2026-05-18T02:21:42.357647+00:00"},{"alias_kind":"arxiv_version","alias_value":"1108.1956v1","created_at":"2026-05-18T02:21:42.357647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.1956","created_at":"2026-05-18T02:21:42.357647+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZD6GEPSTOVG","created_at":"2026-05-18T12:26:18.847500+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZD6GEPSTOVGMWS3","created_at":"2026-05-18T12:26:18.847500+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZD6GEPS","created_at":"2026-05-18T12:26:18.847500+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/2ZD6GEPSTOVGMWS3JGDRDVMAKL","json":"https://pith.science/pith/2ZD6GEPSTOVGMWS3JGDRDVMAKL.json","graph_json":"https://pith.science/api/pith-number/2ZD6GEPSTOVGMWS3JGDRDVMAKL/graph.json","events_json":"https://pith.science/api/pith-number/2ZD6GEPSTOVGMWS3JGDRDVMAKL/events.json","paper":"https://pith.science/paper/2ZD6GEPS"},"agent_actions":{"view_html":"https://pith.science/pith/2ZD6GEPSTOVGMWS3JGDRDVMAKL","download_json":"https://pith.science/pith/2ZD6GEPSTOVGMWS3JGDRDVMAKL.json","view_paper":"https://pith.science/paper/2ZD6GEPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1108.1956&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZD6GEPSTOVGMWS3JGDRDVMAKL/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZD6GEPSTOVGMWS3JGDRDVMAKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZD6GEPSTOVGMWS3JGDRDVMAKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZD6GEPSTOVGMWS3JGDRDVMAKL/action/storage_attestation","attest_author":"https://pith.science/pith/2ZD6GEPSTOVGMWS3JGDRDVMAKL/action/author_attestation","sign_citation":"https://pith.science/pith/2ZD6GEPSTOVGMWS3JGDRDVMAKL/action/citation_signature","submit_replication":"https://pith.science/pith/2ZD6GEPSTOVGMWS3JGDRDVMAKL/action/replication_record"}},"created_at":"2026-05-18T02:21:42.357647+00:00","updated_at":"2026-05-18T02:21:42.357647+00:00"}