{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FS34KIABY7QELGZGLPTSYLFU4O","short_pith_number":"pith:FS34KIAB","schema_version":"1.0","canonical_sha256":"2cb7c52001c7e0459b265be72c2cb4e3bf83ee57cfdc37accce1cb2848269bd4","source":{"kind":"arxiv","id":"2203.14276","version":3},"attestation_state":"computed","paper":{"title":"Example-based Hypernetworks for Out-of-Distribution Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eyal Ben-David, Gal Chechik, Ohad Amosy, Roi Reichart, Tomer Volk","submitted_at":"2022-03-27T11:10:10Z","abstract_excerpt":"As Natural Language Processing (NLP) algorithms continually achieve new milestones, out-of-distribution generalization remains a significant challenge. This paper addresses the issue of multi-source adaptation for unfamiliar domains: We leverage labeled data from multiple source domains to generalize to unknown target domains at training. Our innovative framework employs example-based Hypernetwork adaptation: a T5 encoder-decoder initially generates a unique signature from an input example, embedding it within the source domains' semantic space. This signature is subsequently utilized by a Hyp"},"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":"2203.14276","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-27T11:10:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8598ad0aca1075a5dc1e4168a23144d920c03c284d9000798615a1e12f2904ac","abstract_canon_sha256":"34c93828c5f4682646fb5c95586b1ca58829925572b68b8d45760572a662f207"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:24.700392Z","signature_b64":"AI9UVDE07MpUEIgtaT7tcnpEoFP9DqBonGVzfDAnFYjXIGFNrLwlzyehaaK5A6Z9jycrvGgJl1xsRk5n5Et8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb7c52001c7e0459b265be72c2cb4e3bf83ee57cfdc37accce1cb2848269bd4","last_reissued_at":"2026-07-05T07:02:24.699834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:24.699834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Example-based Hypernetworks for Out-of-Distribution Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eyal Ben-David, Gal Chechik, Ohad Amosy, Roi Reichart, Tomer Volk","submitted_at":"2022-03-27T11:10:10Z","abstract_excerpt":"As Natural Language Processing (NLP) algorithms continually achieve new milestones, out-of-distribution generalization remains a significant challenge. This paper addresses the issue of multi-source adaptation for unfamiliar domains: We leverage labeled data from multiple source domains to generalize to unknown target domains at training. Our innovative framework employs example-based Hypernetwork adaptation: a T5 encoder-decoder initially generates a unique signature from an input example, embedding it within the source domains' semantic space. This signature is subsequently utilized by a Hyp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14276","kind":"arxiv","version":3},"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/2203.14276/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":"2203.14276","created_at":"2026-07-05T07:02:24.699906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14276v3","created_at":"2026-07-05T07:02:24.699906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14276","created_at":"2026-07-05T07:02:24.699906+00:00"},{"alias_kind":"pith_short_12","alias_value":"FS34KIABY7QE","created_at":"2026-07-05T07:02:24.699906+00:00"},{"alias_kind":"pith_short_16","alias_value":"FS34KIABY7QELGZG","created_at":"2026-07-05T07:02:24.699906+00:00"},{"alias_kind":"pith_short_8","alias_value":"FS34KIAB","created_at":"2026-07-05T07:02:24.699906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12670","citing_title":"Discerning and quantifying high frequency activities in EEG under normal and epileptic conditions","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O","json":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O.json","graph_json":"https://pith.science/api/pith-number/FS34KIABY7QELGZGLPTSYLFU4O/graph.json","events_json":"https://pith.science/api/pith-number/FS34KIABY7QELGZGLPTSYLFU4O/events.json","paper":"https://pith.science/paper/FS34KIAB"},"agent_actions":{"view_html":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O","download_json":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O.json","view_paper":"https://pith.science/paper/FS34KIAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14276&json=true","fetch_graph":"https://pith.science/api/pith-number/FS34KIABY7QELGZGLPTSYLFU4O/graph.json","fetch_events":"https://pith.science/api/pith-number/FS34KIABY7QELGZGLPTSYLFU4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O/action/storage_attestation","attest_author":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O/action/author_attestation","sign_citation":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O/action/citation_signature","submit_replication":"https://pith.science/pith/FS34KIABY7QELGZGLPTSYLFU4O/action/replication_record"}},"created_at":"2026-07-05T07:02:24.699906+00:00","updated_at":"2026-07-05T07:02:24.699906+00:00"}