{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AOYCR7IFOTW7OC7VTTWGBY44EY","short_pith_number":"pith:AOYCR7IF","schema_version":"1.0","canonical_sha256":"03b028fd0574edf70bf59cec60e39c262c840bbac65307cb9203b4423061e087","source":{"kind":"arxiv","id":"2006.00555","version":3},"attestation_state":"computed","paper":{"title":"Transferring Inductive Biases through Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mostafa Dehghani, Samira Abnar, Willem Zuidema","submitted_at":"2020-05-31T16:34:08Z","abstract_excerpt":"Having the right inductive biases can be crucial in many tasks or scenarios where data or computing resources are a limiting factor, or where training data is not perfectly representative of the conditions at test time. However, defining, designing and efficiently adapting inductive biases is not necessarily straightforward. In this paper, we explore the power of knowledge distillation for transferring the effect of inductive biases from one model to another. We consider families of models with different inductive biases, LSTMs vs. Transformers and CNNs vs. MLPs, in the context of tasks and sc"},"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":"2006.00555","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-31T16:34:08Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4299cd4ee746b6c25a2d2d35e87fe5dfb3a3fa557f0403ab0c8dc3beec8c4f50","abstract_canon_sha256":"cfa2354a5d6eca098d74a88838c80e6971ff44ce77dd118338fb01422de6f311"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:58.762308Z","signature_b64":"GiBcJt/vLNznpqhNWs6OCHKFyn0Izcgd92xW4JkZ8gSRqmgsi5tZ0tcNv2norEoS3Y5laF48aIdFzZMSx5+dCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03b028fd0574edf70bf59cec60e39c262c840bbac65307cb9203b4423061e087","last_reissued_at":"2026-07-05T01:39:58.761823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:58.761823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferring Inductive Biases through Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mostafa Dehghani, Samira Abnar, Willem Zuidema","submitted_at":"2020-05-31T16:34:08Z","abstract_excerpt":"Having the right inductive biases can be crucial in many tasks or scenarios where data or computing resources are a limiting factor, or where training data is not perfectly representative of the conditions at test time. However, defining, designing and efficiently adapting inductive biases is not necessarily straightforward. In this paper, we explore the power of knowledge distillation for transferring the effect of inductive biases from one model to another. We consider families of models with different inductive biases, LSTMs vs. Transformers and CNNs vs. MLPs, in the context of tasks and sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00555","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/2006.00555/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":"2006.00555","created_at":"2026-07-05T01:39:58.761882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.00555v3","created_at":"2026-07-05T01:39:58.761882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00555","created_at":"2026-07-05T01:39:58.761882+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOYCR7IFOTW7","created_at":"2026-07-05T01:39:58.761882+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOYCR7IFOTW7OC7V","created_at":"2026-07-05T01:39:58.761882+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOYCR7IF","created_at":"2026-07-05T01:39:58.761882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19609","citing_title":"Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY","json":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY.json","graph_json":"https://pith.science/api/pith-number/AOYCR7IFOTW7OC7VTTWGBY44EY/graph.json","events_json":"https://pith.science/api/pith-number/AOYCR7IFOTW7OC7VTTWGBY44EY/events.json","paper":"https://pith.science/paper/AOYCR7IF"},"agent_actions":{"view_html":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY","download_json":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY.json","view_paper":"https://pith.science/paper/AOYCR7IF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.00555&json=true","fetch_graph":"https://pith.science/api/pith-number/AOYCR7IFOTW7OC7VTTWGBY44EY/graph.json","fetch_events":"https://pith.science/api/pith-number/AOYCR7IFOTW7OC7VTTWGBY44EY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY/action/storage_attestation","attest_author":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY/action/author_attestation","sign_citation":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY/action/citation_signature","submit_replication":"https://pith.science/pith/AOYCR7IFOTW7OC7VTTWGBY44EY/action/replication_record"}},"created_at":"2026-07-05T01:39:58.761882+00:00","updated_at":"2026-07-05T01:39:58.761882+00:00"}