{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJZOZKNL26OSUUNKXVIKA4MYN7","short_pith_number":"pith:ZJZOZKNL","schema_version":"1.0","canonical_sha256":"ca72eca9abd79d2a51aabd50a071986fd928c17321643f3b0abe1f868c519f73","source":{"kind":"arxiv","id":"2506.18629","version":2},"attestation_state":"computed","paper":{"title":"On Equivariant Model Selection through the Lens of Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Timans, Dharmesh Tailor, Erik J. Bekkers, Putri A. van der Linden","submitted_at":"2025-06-23T13:35:06Z","abstract_excerpt":"Equivariant models leverage prior knowledge on symmetries to improve predictive performance, but misspecified architectural constraints can harm it instead. While work has explored learning or relaxing constraints, selecting among pretrained models with varying symmetry biases remains challenging. We examine this model selection task from an uncertainty-aware perspective, comparing frequentist (via Conformal Prediction), Bayesian (via the marginal likelihood), and calibration-based measures to naive error-based evaluation. We find that uncertainty metrics generally align with predictive perfor"},"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":"2506.18629","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T13:35:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d981550139e1a9cc03273929e2a5f93facdb038914cea3be26279699e9fb3873","abstract_canon_sha256":"f1a2c4a75df91e4d4d33255a3adaefcdab0f20693c95280ba65b5cd7ac8dd687"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:24.154961Z","signature_b64":"+4OM+0TXygqZDWw2cXSLFEjx/BeJ43g0Fp4bNMQ2X/EpviJXkq/Wy68kK3uEF0vK7YSlJ4aJRZ//KmlTCNs/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca72eca9abd79d2a51aabd50a071986fd928c17321643f3b0abe1f868c519f73","last_reissued_at":"2026-07-05T11:37:24.154338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:24.154338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Equivariant Model Selection through the Lens of Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Timans, Dharmesh Tailor, Erik J. Bekkers, Putri A. van der Linden","submitted_at":"2025-06-23T13:35:06Z","abstract_excerpt":"Equivariant models leverage prior knowledge on symmetries to improve predictive performance, but misspecified architectural constraints can harm it instead. While work has explored learning or relaxing constraints, selecting among pretrained models with varying symmetry biases remains challenging. We examine this model selection task from an uncertainty-aware perspective, comparing frequentist (via Conformal Prediction), Bayesian (via the marginal likelihood), and calibration-based measures to naive error-based evaluation. We find that uncertainty metrics generally align with predictive perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18629","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/2506.18629/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":"2506.18629","created_at":"2026-07-05T11:37:24.154413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18629v2","created_at":"2026-07-05T11:37:24.154413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18629","created_at":"2026-07-05T11:37:24.154413+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJZOZKNL26OS","created_at":"2026-07-05T11:37:24.154413+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJZOZKNL26OSUUNK","created_at":"2026-07-05T11:37:24.154413+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJZOZKNL","created_at":"2026-07-05T11:37:24.154413+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/ZJZOZKNL26OSUUNKXVIKA4MYN7","json":"https://pith.science/pith/ZJZOZKNL26OSUUNKXVIKA4MYN7.json","graph_json":"https://pith.science/api/pith-number/ZJZOZKNL26OSUUNKXVIKA4MYN7/graph.json","events_json":"https://pith.science/api/pith-number/ZJZOZKNL26OSUUNKXVIKA4MYN7/events.json","paper":"https://pith.science/paper/ZJZOZKNL"},"agent_actions":{"view_html":"https://pith.science/pith/ZJZOZKNL26OSUUNKXVIKA4MYN7","download_json":"https://pith.science/pith/ZJZOZKNL26OSUUNKXVIKA4MYN7.json","view_paper":"https://pith.science/paper/ZJZOZKNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18629&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJZOZKNL26OSUUNKXVIKA4MYN7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJZOZKNL26OSUUNKXVIKA4MYN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJZOZKNL26OSUUNKXVIKA4MYN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJZOZKNL26OSUUNKXVIKA4MYN7/action/storage_attestation","attest_author":"https://pith.science/pith/ZJZOZKNL26OSUUNKXVIKA4MYN7/action/author_attestation","sign_citation":"https://pith.science/pith/ZJZOZKNL26OSUUNKXVIKA4MYN7/action/citation_signature","submit_replication":"https://pith.science/pith/ZJZOZKNL26OSUUNKXVIKA4MYN7/action/replication_record"}},"created_at":"2026-07-05T11:37:24.154413+00:00","updated_at":"2026-07-05T11:37:24.154413+00:00"}