{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NJK6GN7FRQK4DIC6OVLLHKZKFO","short_pith_number":"pith:NJK6GN7F","schema_version":"1.0","canonical_sha256":"6a55e337e58c15c1a05e7556b3ab2a2ba72b09185a621e7c5a06af2b14af3da0","source":{"kind":"arxiv","id":"2502.05364","version":2},"attestation_state":"computed","paper":{"title":"Hypencoder: Hypernetworks for Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Hamed Zamani, Hansi Zeng, Julian Killingback","submitted_at":"2025-02-07T22:31:38Z","abstract_excerpt":"Existing information retrieval systems are largely constrained by their reliance on vector inner products to assess query-document relevance, which naturally limits the expressiveness of the relevance score they can produce. We propose a new paradigm; instead of representing a query as a vector, we use a small neural network that acts as a learned query-specific relevance function. This small neural network takes a document representation as input (in this work we use a single vector) and produces a scalar relevance score. To produce the small neural network we use a hypernetwork, a network th"},"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":"2502.05364","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-07T22:31:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53e60a85b1406b6cf7e137f84b281d1c1ece4b598e1e85fa9d8ef8b6edef2b9e","abstract_canon_sha256":"54be4cfd938e5de69bff2d9308575889badf9df93f1f30edb0e0de9b4cd3eef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:21.342616Z","signature_b64":"EQ8OKA58jEwzLCfAw0XfsTOIv0FZIobboPmpzlFCJVqxUOHoV1X/NMGmMlI02YBXBaHsVkm7pWZpPdy0lE0IAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a55e337e58c15c1a05e7556b3ab2a2ba72b09185a621e7c5a06af2b14af3da0","last_reissued_at":"2026-07-05T10:57:21.342106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:21.342106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypencoder: Hypernetworks for Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Hamed Zamani, Hansi Zeng, Julian Killingback","submitted_at":"2025-02-07T22:31:38Z","abstract_excerpt":"Existing information retrieval systems are largely constrained by their reliance on vector inner products to assess query-document relevance, which naturally limits the expressiveness of the relevance score they can produce. We propose a new paradigm; instead of representing a query as a vector, we use a small neural network that acts as a learned query-specific relevance function. This small neural network takes a document representation as input (in this work we use a single vector) and produces a scalar relevance score. To produce the small neural network we use a hypernetwork, a network th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05364","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/2502.05364/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":"2502.05364","created_at":"2026-07-05T10:57:21.342171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05364v2","created_at":"2026-07-05T10:57:21.342171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05364","created_at":"2026-07-05T10:57:21.342171+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJK6GN7FRQK4","created_at":"2026-07-05T10:57:21.342171+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJK6GN7FRQK4DIC6","created_at":"2026-07-05T10:57:21.342171+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJK6GN7F","created_at":"2026-07-05T10:57:21.342171+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/NJK6GN7FRQK4DIC6OVLLHKZKFO","json":"https://pith.science/pith/NJK6GN7FRQK4DIC6OVLLHKZKFO.json","graph_json":"https://pith.science/api/pith-number/NJK6GN7FRQK4DIC6OVLLHKZKFO/graph.json","events_json":"https://pith.science/api/pith-number/NJK6GN7FRQK4DIC6OVLLHKZKFO/events.json","paper":"https://pith.science/paper/NJK6GN7F"},"agent_actions":{"view_html":"https://pith.science/pith/NJK6GN7FRQK4DIC6OVLLHKZKFO","download_json":"https://pith.science/pith/NJK6GN7FRQK4DIC6OVLLHKZKFO.json","view_paper":"https://pith.science/paper/NJK6GN7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05364&json=true","fetch_graph":"https://pith.science/api/pith-number/NJK6GN7FRQK4DIC6OVLLHKZKFO/graph.json","fetch_events":"https://pith.science/api/pith-number/NJK6GN7FRQK4DIC6OVLLHKZKFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJK6GN7FRQK4DIC6OVLLHKZKFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJK6GN7FRQK4DIC6OVLLHKZKFO/action/storage_attestation","attest_author":"https://pith.science/pith/NJK6GN7FRQK4DIC6OVLLHKZKFO/action/author_attestation","sign_citation":"https://pith.science/pith/NJK6GN7FRQK4DIC6OVLLHKZKFO/action/citation_signature","submit_replication":"https://pith.science/pith/NJK6GN7FRQK4DIC6OVLLHKZKFO/action/replication_record"}},"created_at":"2026-07-05T10:57:21.342171+00:00","updated_at":"2026-07-05T10:57:21.342171+00:00"}