{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HQHWS2TA52EKETEEKSJZE7VMXJ","short_pith_number":"pith:HQHWS2TA","schema_version":"1.0","canonical_sha256":"3c0f696a60ee88a24c845493927eacba4f8b19d6ced75d9f01a6f6ce75d26dcf","source":{"kind":"arxiv","id":"2310.01647","version":2},"attestation_state":"computed","paper":{"title":"Equivariant Adaptation of Large Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnab Kumar Mondal, Sai Rajeswar, S\\'ekou-Oumar Kaba, Siamak Ravanbakhsh, Siba Smarak Panigrahi","submitted_at":"2023-10-02T21:21:28Z","abstract_excerpt":"Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to higher sample efficiency and more accurate and robust predictions. However, redesigning each component of prevalent deep neural network architectures to achieve chosen equivariance is a difficult problem and can result in a computationally expensive network during both training and inference. A recently proposed alternative towards equivariance that removes the architectural constraints is to use a simple canonicalization network that transforms the input to a"},"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":"2310.01647","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T21:21:28Z","cross_cats_sorted":[],"title_canon_sha256":"dee72a074951ba11bff568d031d34a3d777f501700ec0f41c9fd81c546229aeb","abstract_canon_sha256":"e56542a2a7321bff323eb14e5ac1cf9d68eaab3dbcfc74b2a0b2c7c754610ab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:34.912059Z","signature_b64":"/vrwg3VQ189sTaZFxcJBOGZdpI4bu+c3PGgzmxYv/1W2rXyM8UnfeQMT3r9D4ZB5xCS8KFYYd2B3TDmgwskaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c0f696a60ee88a24c845493927eacba4f8b19d6ced75d9f01a6f6ce75d26dcf","last_reissued_at":"2026-07-05T07:06:34.911652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:34.911652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivariant Adaptation of Large Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnab Kumar Mondal, Sai Rajeswar, S\\'ekou-Oumar Kaba, Siamak Ravanbakhsh, Siba Smarak Panigrahi","submitted_at":"2023-10-02T21:21:28Z","abstract_excerpt":"Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to higher sample efficiency and more accurate and robust predictions. However, redesigning each component of prevalent deep neural network architectures to achieve chosen equivariance is a difficult problem and can result in a computationally expensive network during both training and inference. A recently proposed alternative towards equivariance that removes the architectural constraints is to use a simple canonicalization network that transforms the input to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01647","kind":"arxiv","version":2},"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/2310.01647/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":"2310.01647","created_at":"2026-07-05T07:06:34.911714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01647v2","created_at":"2026-07-05T07:06:34.911714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01647","created_at":"2026-07-05T07:06:34.911714+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQHWS2TA52EK","created_at":"2026-07-05T07:06:34.911714+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQHWS2TA52EKETEE","created_at":"2026-07-05T07:06:34.911714+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQHWS2TA","created_at":"2026-07-05T07:06:34.911714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.11218","citing_title":"Geometrically Constrained and Token-Based Probabilistic Spatial Transformers","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ","json":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ.json","graph_json":"https://pith.science/api/pith-number/HQHWS2TA52EKETEEKSJZE7VMXJ/graph.json","events_json":"https://pith.science/api/pith-number/HQHWS2TA52EKETEEKSJZE7VMXJ/events.json","paper":"https://pith.science/paper/HQHWS2TA"},"agent_actions":{"view_html":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ","download_json":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ.json","view_paper":"https://pith.science/paper/HQHWS2TA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01647&json=true","fetch_graph":"https://pith.science/api/pith-number/HQHWS2TA52EKETEEKSJZE7VMXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HQHWS2TA52EKETEEKSJZE7VMXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ/action/storage_attestation","attest_author":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ/action/author_attestation","sign_citation":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ/action/citation_signature","submit_replication":"https://pith.science/pith/HQHWS2TA52EKETEEKSJZE7VMXJ/action/replication_record"}},"created_at":"2026-07-05T07:06:34.911714+00:00","updated_at":"2026-07-05T07:06:34.911714+00:00"}