{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZT3PHULSEZCAXTKEZLDAF7YT3B","short_pith_number":"pith:ZT3PHULS","schema_version":"1.0","canonical_sha256":"ccf6f3d17226440bcd44cac602ff13d85bb82fa1d0aa13f7e3d3d3b0072e1789","source":{"kind":"arxiv","id":"2410.09655","version":1},"attestation_state":"computed","paper":{"title":"Interpolated-MLPs: Controllable Inductive Bias","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gregor Bachmann, Jordan Hong, Keyu Bai, Sean Wu","submitted_at":"2024-10-12T21:20:21Z","abstract_excerpt":"Due to their weak inductive bias, Multi-Layer Perceptrons (MLPs) have subpar performance at low-compute levels compared to standard architectures such as convolution-based networks (CNN). Recent work, however, has shown that the performance gap drastically reduces as the amount of compute is increased without changing the amount of inductive bias. In this work, we study the converse: in the low-compute regime, how does the incremental increase of inductive bias affect performance? To quantify inductive bias, we propose a \"soft MLP\" approach, which we coin Interpolated MLP (I-MLP). We control t"},"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":"2410.09655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-12T21:20:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fd02ec70e1bd11f669ab4e969cbe24164e0310d0f9bb8a0adc3574cdb6bebc85","abstract_canon_sha256":"3f067b85a0c47911275209611a6d619f9e1af5de5de605d65e8db2c37d0396ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:42.143939Z","signature_b64":"vDTDd4ovsu4nvS5xzij748JGKunEzZrKebtlfzQ2q8LCK5dghC24KsplNSm8suanKPjrHKvFjji13AX8ckU4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccf6f3d17226440bcd44cac602ff13d85bb82fa1d0aa13f7e3d3d3b0072e1789","last_reissued_at":"2026-07-05T09:19:42.143392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:42.143392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpolated-MLPs: Controllable Inductive Bias","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gregor Bachmann, Jordan Hong, Keyu Bai, Sean Wu","submitted_at":"2024-10-12T21:20:21Z","abstract_excerpt":"Due to their weak inductive bias, Multi-Layer Perceptrons (MLPs) have subpar performance at low-compute levels compared to standard architectures such as convolution-based networks (CNN). Recent work, however, has shown that the performance gap drastically reduces as the amount of compute is increased without changing the amount of inductive bias. In this work, we study the converse: in the low-compute regime, how does the incremental increase of inductive bias affect performance? To quantify inductive bias, we propose a \"soft MLP\" approach, which we coin Interpolated MLP (I-MLP). We control t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09655","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/2410.09655/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":"2410.09655","created_at":"2026-07-05T09:19:42.143454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09655v1","created_at":"2026-07-05T09:19:42.143454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09655","created_at":"2026-07-05T09:19:42.143454+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZT3PHULSEZCA","created_at":"2026-07-05T09:19:42.143454+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZT3PHULSEZCAXTKE","created_at":"2026-07-05T09:19:42.143454+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZT3PHULS","created_at":"2026-07-05T09:19:42.143454+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/ZT3PHULSEZCAXTKEZLDAF7YT3B","json":"https://pith.science/pith/ZT3PHULSEZCAXTKEZLDAF7YT3B.json","graph_json":"https://pith.science/api/pith-number/ZT3PHULSEZCAXTKEZLDAF7YT3B/graph.json","events_json":"https://pith.science/api/pith-number/ZT3PHULSEZCAXTKEZLDAF7YT3B/events.json","paper":"https://pith.science/paper/ZT3PHULS"},"agent_actions":{"view_html":"https://pith.science/pith/ZT3PHULSEZCAXTKEZLDAF7YT3B","download_json":"https://pith.science/pith/ZT3PHULSEZCAXTKEZLDAF7YT3B.json","view_paper":"https://pith.science/paper/ZT3PHULS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09655&json=true","fetch_graph":"https://pith.science/api/pith-number/ZT3PHULSEZCAXTKEZLDAF7YT3B/graph.json","fetch_events":"https://pith.science/api/pith-number/ZT3PHULSEZCAXTKEZLDAF7YT3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZT3PHULSEZCAXTKEZLDAF7YT3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZT3PHULSEZCAXTKEZLDAF7YT3B/action/storage_attestation","attest_author":"https://pith.science/pith/ZT3PHULSEZCAXTKEZLDAF7YT3B/action/author_attestation","sign_citation":"https://pith.science/pith/ZT3PHULSEZCAXTKEZLDAF7YT3B/action/citation_signature","submit_replication":"https://pith.science/pith/ZT3PHULSEZCAXTKEZLDAF7YT3B/action/replication_record"}},"created_at":"2026-07-05T09:19:42.143454+00:00","updated_at":"2026-07-05T09:19:42.143454+00:00"}