{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FZ4GX2M3AS5ZHDDTVCY4573XVY","short_pith_number":"pith:FZ4GX2M3","schema_version":"1.0","canonical_sha256":"2e786be99b04bb938c73a8b1ceff77ae246d2f5cbbded80ecd3abc839a3982c8","source":{"kind":"arxiv","id":"2410.15148","version":1},"attestation_state":"computed","paper":{"title":"Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Akbik, David Schulte, Felix Hamborg","submitted_at":"2024-10-19T16:22:04Z","abstract_excerpt":"Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance strongly. But which task to choose for transfer learning? Prior methods producing useful task rankings are infeasible for large source pools, as they require forward passes through all source language models. We overcome this by introducing Embedding Space Maps (ESMs), light-weight neural networks that approximate the effect of fine-tuning a language model."},"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":"2410.15148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-19T16:22:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66167a72601a0b38a2e70ce3f2a5a6f7c62bbf181424633cb427832ab35be322","abstract_canon_sha256":"1f0e3d75ca0ec909860d1555e42719418abd56c49b602bc8fe690956f107ac08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:51.022002Z","signature_b64":"dgWqZyHvy+CKHNs1SAma4BkUWdfPaqm3S8a71pJFit4JF69B8bxJoQb4rd569LhqdLGKu8snKWLLr++CXPHkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e786be99b04bb938c73a8b1ceff77ae246d2f5cbbded80ecd3abc839a3982c8","last_reissued_at":"2026-07-05T09:22:51.021661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:51.021661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Akbik, David Schulte, Felix Hamborg","submitted_at":"2024-10-19T16:22:04Z","abstract_excerpt":"Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance strongly. But which task to choose for transfer learning? Prior methods producing useful task rankings are infeasible for large source pools, as they require forward passes through all source language models. We overcome this by introducing Embedding Space Maps (ESMs), light-weight neural networks that approximate the effect of fine-tuning a language model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15148","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/2410.15148/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":"2410.15148","created_at":"2026-07-05T09:22:51.021717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15148v1","created_at":"2026-07-05T09:22:51.021717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15148","created_at":"2026-07-05T09:22:51.021717+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZ4GX2M3AS5Z","created_at":"2026-07-05T09:22:51.021717+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZ4GX2M3AS5ZHDDT","created_at":"2026-07-05T09:22:51.021717+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZ4GX2M3","created_at":"2026-07-05T09:22:51.021717+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/FZ4GX2M3AS5ZHDDTVCY4573XVY","json":"https://pith.science/pith/FZ4GX2M3AS5ZHDDTVCY4573XVY.json","graph_json":"https://pith.science/api/pith-number/FZ4GX2M3AS5ZHDDTVCY4573XVY/graph.json","events_json":"https://pith.science/api/pith-number/FZ4GX2M3AS5ZHDDTVCY4573XVY/events.json","paper":"https://pith.science/paper/FZ4GX2M3"},"agent_actions":{"view_html":"https://pith.science/pith/FZ4GX2M3AS5ZHDDTVCY4573XVY","download_json":"https://pith.science/pith/FZ4GX2M3AS5ZHDDTVCY4573XVY.json","view_paper":"https://pith.science/paper/FZ4GX2M3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15148&json=true","fetch_graph":"https://pith.science/api/pith-number/FZ4GX2M3AS5ZHDDTVCY4573XVY/graph.json","fetch_events":"https://pith.science/api/pith-number/FZ4GX2M3AS5ZHDDTVCY4573XVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZ4GX2M3AS5ZHDDTVCY4573XVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZ4GX2M3AS5ZHDDTVCY4573XVY/action/storage_attestation","attest_author":"https://pith.science/pith/FZ4GX2M3AS5ZHDDTVCY4573XVY/action/author_attestation","sign_citation":"https://pith.science/pith/FZ4GX2M3AS5ZHDDTVCY4573XVY/action/citation_signature","submit_replication":"https://pith.science/pith/FZ4GX2M3AS5ZHDDTVCY4573XVY/action/replication_record"}},"created_at":"2026-07-05T09:22:51.021717+00:00","updated_at":"2026-07-05T09:22:51.021717+00:00"}