{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C66IEMEXL55IJK7TZFIYULHMSJ","short_pith_number":"pith:C66IEMEX","schema_version":"1.0","canonical_sha256":"17bc8230975f7a84abf3c9518a2cec92468f7fbab3c4eb13314779706c982b85","source":{"kind":"arxiv","id":"2407.14430","version":1},"attestation_state":"computed","paper":{"title":"The Extrapolation Power of Implicit Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alicia Y. Tsai, Ashwin Ganesh, Juliette Decugis, Laurent El Ghaoui, Max Emerling","submitted_at":"2024-07-19T16:01:37Z","abstract_excerpt":"In this paper, we investigate the extrapolation capabilities of implicit deep learning models in handling unobserved data, where traditional deep neural networks may falter. Implicit models, distinguished by their adaptability in layer depth and incorporation of feedback within their computational graph, are put to the test across various extrapolation scenarios: out-of-distribution, geographical, and temporal shifts. Our experiments consistently demonstrate significant performance advantage with implicit models. Unlike their non-implicit counterparts, which often rely on meticulous architectu"},"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":"2407.14430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T16:01:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fb54b4012593b1e2755a872a3155189247041987b9a44502aa13cd91d5c80ec4","abstract_canon_sha256":"de8e1707a54f44a39155a6324b3c6f3cb838e309823bc6eb369735d5ed1bff1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:12.600960Z","signature_b64":"eKKa2020hOQhDurT5TPv5EJ4vWUUPXDQ/m0yjRAsTWRNGxIPg3+/dl46YoW/syufvJz3VgQ2Gd+RdhkLa4vWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17bc8230975f7a84abf3c9518a2cec92468f7fbab3c4eb13314779706c982b85","last_reissued_at":"2026-07-05T08:46:12.600536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:12.600536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Extrapolation Power of Implicit Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alicia Y. Tsai, Ashwin Ganesh, Juliette Decugis, Laurent El Ghaoui, Max Emerling","submitted_at":"2024-07-19T16:01:37Z","abstract_excerpt":"In this paper, we investigate the extrapolation capabilities of implicit deep learning models in handling unobserved data, where traditional deep neural networks may falter. Implicit models, distinguished by their adaptability in layer depth and incorporation of feedback within their computational graph, are put to the test across various extrapolation scenarios: out-of-distribution, geographical, and temporal shifts. Our experiments consistently demonstrate significant performance advantage with implicit models. Unlike their non-implicit counterparts, which often rely on meticulous architectu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14430","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/2407.14430/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":"2407.14430","created_at":"2026-07-05T08:46:12.600605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14430v1","created_at":"2026-07-05T08:46:12.600605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14430","created_at":"2026-07-05T08:46:12.600605+00:00"},{"alias_kind":"pith_short_12","alias_value":"C66IEMEXL55I","created_at":"2026-07-05T08:46:12.600605+00:00"},{"alias_kind":"pith_short_16","alias_value":"C66IEMEXL55IJK7T","created_at":"2026-07-05T08:46:12.600605+00:00"},{"alias_kind":"pith_short_8","alias_value":"C66IEMEX","created_at":"2026-07-05T08:46:12.600605+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/C66IEMEXL55IJK7TZFIYULHMSJ","json":"https://pith.science/pith/C66IEMEXL55IJK7TZFIYULHMSJ.json","graph_json":"https://pith.science/api/pith-number/C66IEMEXL55IJK7TZFIYULHMSJ/graph.json","events_json":"https://pith.science/api/pith-number/C66IEMEXL55IJK7TZFIYULHMSJ/events.json","paper":"https://pith.science/paper/C66IEMEX"},"agent_actions":{"view_html":"https://pith.science/pith/C66IEMEXL55IJK7TZFIYULHMSJ","download_json":"https://pith.science/pith/C66IEMEXL55IJK7TZFIYULHMSJ.json","view_paper":"https://pith.science/paper/C66IEMEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14430&json=true","fetch_graph":"https://pith.science/api/pith-number/C66IEMEXL55IJK7TZFIYULHMSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/C66IEMEXL55IJK7TZFIYULHMSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C66IEMEXL55IJK7TZFIYULHMSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C66IEMEXL55IJK7TZFIYULHMSJ/action/storage_attestation","attest_author":"https://pith.science/pith/C66IEMEXL55IJK7TZFIYULHMSJ/action/author_attestation","sign_citation":"https://pith.science/pith/C66IEMEXL55IJK7TZFIYULHMSJ/action/citation_signature","submit_replication":"https://pith.science/pith/C66IEMEXL55IJK7TZFIYULHMSJ/action/replication_record"}},"created_at":"2026-07-05T08:46:12.600605+00:00","updated_at":"2026-07-05T08:46:12.600605+00:00"}