{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HCZG55TUYL3L6GUPXNIUOTFSKX","short_pith_number":"pith:HCZG55TU","schema_version":"1.0","canonical_sha256":"38b26ef674c2f6bf1a8fbb51474cb255e266025b5a80561f94d51f56c568ae6a","source":{"kind":"arxiv","id":"2503.05037","version":2},"attestation_state":"computed","paper":{"title":"Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ali Modarressi, Hinrich Schuetze, Mohsen Fayyaz, Nanyun Peng","submitted_at":"2025-03-06T23:23:13Z","abstract_excerpt":"Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream failures. In this work, we repurpose a relation extraction dataset (e.g., Re-DocRED) to design controlled experiments that quantify the impact of heuristic biases, such as a preference for shorter documents, on retrievers like Dragon+ and Contriever. We uncover major vulnerabilities, showing retrievers favor shorter documents, early positions, repeated entiti"},"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":"2503.05037","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T23:23:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"940438f4abcd9ed978107ca1254cbe27df24ddf065ddc135fad6765d36b6c3f4","abstract_canon_sha256":"e90747951218bc81b5f6fc946a3dc0d34f35ee88e6d2a5d260f1d9349cf15ebb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:27.959528Z","signature_b64":"q55lhuhbOsHYWq+7ComfcxFqY97fCjtyECu3qJk68ZTfmmrBsC0vS0Tnx7AYBlaIUjzhAhGSmR/lHkJ1+LkLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38b26ef674c2f6bf1a8fbb51474cb255e266025b5a80561f94d51f56c568ae6a","last_reissued_at":"2026-07-05T11:14:27.958792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:27.958792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ali Modarressi, Hinrich Schuetze, Mohsen Fayyaz, Nanyun Peng","submitted_at":"2025-03-06T23:23:13Z","abstract_excerpt":"Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream failures. In this work, we repurpose a relation extraction dataset (e.g., Re-DocRED) to design controlled experiments that quantify the impact of heuristic biases, such as a preference for shorter documents, on retrievers like Dragon+ and Contriever. We uncover major vulnerabilities, showing retrievers favor shorter documents, early positions, repeated entiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05037","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/2503.05037/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":"2503.05037","created_at":"2026-07-05T11:14:27.958887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05037v2","created_at":"2026-07-05T11:14:27.958887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05037","created_at":"2026-07-05T11:14:27.958887+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCZG55TUYL3L","created_at":"2026-07-05T11:14:27.958887+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCZG55TUYL3L6GUP","created_at":"2026-07-05T11:14:27.958887+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCZG55TU","created_at":"2026-07-05T11:14:27.958887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.04390","citing_title":"Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX","json":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX.json","graph_json":"https://pith.science/api/pith-number/HCZG55TUYL3L6GUPXNIUOTFSKX/graph.json","events_json":"https://pith.science/api/pith-number/HCZG55TUYL3L6GUPXNIUOTFSKX/events.json","paper":"https://pith.science/paper/HCZG55TU"},"agent_actions":{"view_html":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX","download_json":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX.json","view_paper":"https://pith.science/paper/HCZG55TU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05037&json=true","fetch_graph":"https://pith.science/api/pith-number/HCZG55TUYL3L6GUPXNIUOTFSKX/graph.json","fetch_events":"https://pith.science/api/pith-number/HCZG55TUYL3L6GUPXNIUOTFSKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX/action/storage_attestation","attest_author":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX/action/author_attestation","sign_citation":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX/action/citation_signature","submit_replication":"https://pith.science/pith/HCZG55TUYL3L6GUPXNIUOTFSKX/action/replication_record"}},"created_at":"2026-07-05T11:14:27.958887+00:00","updated_at":"2026-07-05T11:14:27.958887+00:00"}