{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZJVMYSWQTHFI5CYFDD77NABIME","short_pith_number":"pith:ZJVMYSWQ","schema_version":"1.0","canonical_sha256":"ca6acc4ad099ca8e8b0518fff68028612a2dbc29afd33ab95fc4c6b09b4579ea","source":{"kind":"arxiv","id":"2102.10697","version":2},"attestation_state":"computed","paper":{"title":"Pruning the Index Contents for Memory Efficient Open-Domain QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Karel Ondrej, Martin Docekal, Martin Fajcik, Pavel Smrz","submitted_at":"2021-02-21T21:56:38Z","abstract_excerpt":"This work presents a novel pipeline that demonstrates what is achievable with a combined effort of state-of-the-art approaches. Specifically, it proposes the novel R2-D2 (Rank twice, reaD twice) pipeline composed of retriever, passage reranker, extractive reader, generative reader and a simple way to combine them. Furthermore, previous work often comes with a massive index of external documents that scales in the order of tens of GiB. This work presents a simple approach for pruning the contents of a massive index such that the open-domain QA system altogether with index, OS, and library compo"},"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":"2102.10697","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-21T21:56:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"53e2e0e0bbdc52a6fece7ead831c785024d412b405281f4dde02a9878c312114","abstract_canon_sha256":"5e085dd659331f0c1771eef57ccf84fabbf1c3b5eedab4facf2e7b54feff4749"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:43.737925Z","signature_b64":"E4uZQK2xf3i5IAarB73gvH7jzd/rir7rSpF55arFlLYo1yWV7f9xR8zFKxVP+56gTBEaHNmYBINSJeCPizhsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6acc4ad099ca8e8b0518fff68028612a2dbc29afd33ab95fc4c6b09b4579ea","last_reissued_at":"2026-07-05T02:30:43.737427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:43.737427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pruning the Index Contents for Memory Efficient Open-Domain QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Karel Ondrej, Martin Docekal, Martin Fajcik, Pavel Smrz","submitted_at":"2021-02-21T21:56:38Z","abstract_excerpt":"This work presents a novel pipeline that demonstrates what is achievable with a combined effort of state-of-the-art approaches. Specifically, it proposes the novel R2-D2 (Rank twice, reaD twice) pipeline composed of retriever, passage reranker, extractive reader, generative reader and a simple way to combine them. Furthermore, previous work often comes with a massive index of external documents that scales in the order of tens of GiB. This work presents a simple approach for pruning the contents of a massive index such that the open-domain QA system altogether with index, OS, and library compo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10697","kind":"arxiv","version":2},"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/2102.10697/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":"2102.10697","created_at":"2026-07-05T02:30:43.737480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10697v2","created_at":"2026-07-05T02:30:43.737480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10697","created_at":"2026-07-05T02:30:43.737480+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJVMYSWQTHFI","created_at":"2026-07-05T02:30:43.737480+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJVMYSWQTHFI5CYF","created_at":"2026-07-05T02:30:43.737480+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJVMYSWQ","created_at":"2026-07-05T02:30:43.737480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02814","citing_title":"Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME","json":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME.json","graph_json":"https://pith.science/api/pith-number/ZJVMYSWQTHFI5CYFDD77NABIME/graph.json","events_json":"https://pith.science/api/pith-number/ZJVMYSWQTHFI5CYFDD77NABIME/events.json","paper":"https://pith.science/paper/ZJVMYSWQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME","download_json":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME.json","view_paper":"https://pith.science/paper/ZJVMYSWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10697&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJVMYSWQTHFI5CYFDD77NABIME/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJVMYSWQTHFI5CYFDD77NABIME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME/action/storage_attestation","attest_author":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME/action/author_attestation","sign_citation":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME/action/citation_signature","submit_replication":"https://pith.science/pith/ZJVMYSWQTHFI5CYFDD77NABIME/action/replication_record"}},"created_at":"2026-07-05T02:30:43.737480+00:00","updated_at":"2026-07-05T02:30:43.737480+00:00"}