{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A42TMDX4ALTPID6IFYPEJ4UTWP","short_pith_number":"pith:A42TMDX4","schema_version":"1.0","canonical_sha256":"0735360efc02e6f40fc82e1e44f293b3cf91e01b813b789d290ef307d91e21cc","source":{"kind":"arxiv","id":"2110.02065","version":1},"attestation_state":"computed","paper":{"title":"SDR: Efficient Neural Re-ranking using Succinct Document Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Amir Ingber, Amit Portnoy, Besnik Fetahu, Nachshon Cohen","submitted_at":"2021-10-03T07:43:16Z","abstract_excerpt":"BERT based ranking models have achieved superior performance on various information retrieval tasks. However, the large number of parameters and complex self-attention operation come at a significant latency overhead. To remedy this, recent works propose late-interaction architectures, which allow pre-computation of intermediate document representations, thus reducing the runtime latency. Nonetheless, having solved the immediate latency issue, these methods now introduce storage costs and network fetching latency, which limits their adoption in real-life production systems.\n  In this work, we "},"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":"2110.02065","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-10-03T07:43:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"066c3684249f48794bb3492a71dd64b8dd697bfd187d98f0c2e23c298d78791b","abstract_canon_sha256":"d504efc57bded2f1e6d47d019093362df381b50036270b0234d62518e1a994c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:16.036379Z","signature_b64":"JD9gZznVl3gsNeg001UHtrfZIrqc2fqDjMELMmGw+cTtzAMY7hJeRX3XbYYRUdmHgKbSYliN2t3aoyqBYZ02Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0735360efc02e6f40fc82e1e44f293b3cf91e01b813b789d290ef307d91e21cc","last_reissued_at":"2026-07-05T03:20:16.035907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:16.035907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDR: Efficient Neural Re-ranking using Succinct Document Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Amir Ingber, Amit Portnoy, Besnik Fetahu, Nachshon Cohen","submitted_at":"2021-10-03T07:43:16Z","abstract_excerpt":"BERT based ranking models have achieved superior performance on various information retrieval tasks. However, the large number of parameters and complex self-attention operation come at a significant latency overhead. To remedy this, recent works propose late-interaction architectures, which allow pre-computation of intermediate document representations, thus reducing the runtime latency. Nonetheless, having solved the immediate latency issue, these methods now introduce storage costs and network fetching latency, which limits their adoption in real-life production systems.\n  In this work, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02065","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.02065/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.02065","created_at":"2026-07-05T03:20:16.035958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02065v1","created_at":"2026-07-05T03:20:16.035958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02065","created_at":"2026-07-05T03:20:16.035958+00:00"},{"alias_kind":"pith_short_12","alias_value":"A42TMDX4ALTP","created_at":"2026-07-05T03:20:16.035958+00:00"},{"alias_kind":"pith_short_16","alias_value":"A42TMDX4ALTPID6I","created_at":"2026-07-05T03:20:16.035958+00:00"},{"alias_kind":"pith_short_8","alias_value":"A42TMDX4","created_at":"2026-07-05T03:20:16.035958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18231","citing_title":"NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP","json":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP.json","graph_json":"https://pith.science/api/pith-number/A42TMDX4ALTPID6IFYPEJ4UTWP/graph.json","events_json":"https://pith.science/api/pith-number/A42TMDX4ALTPID6IFYPEJ4UTWP/events.json","paper":"https://pith.science/paper/A42TMDX4"},"agent_actions":{"view_html":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP","download_json":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP.json","view_paper":"https://pith.science/paper/A42TMDX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02065&json=true","fetch_graph":"https://pith.science/api/pith-number/A42TMDX4ALTPID6IFYPEJ4UTWP/graph.json","fetch_events":"https://pith.science/api/pith-number/A42TMDX4ALTPID6IFYPEJ4UTWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP/action/storage_attestation","attest_author":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP/action/author_attestation","sign_citation":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP/action/citation_signature","submit_replication":"https://pith.science/pith/A42TMDX4ALTPID6IFYPEJ4UTWP/action/replication_record"}},"created_at":"2026-07-05T03:20:16.035958+00:00","updated_at":"2026-07-05T03:20:16.035958+00:00"}