{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7GWX2CYTVS3FUVVIY6NMGMDTGU","short_pith_number":"pith:7GWX2CYT","canonical_record":{"source":{"id":"2410.23179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T16:36:59Z","cross_cats_sorted":[],"title_canon_sha256":"858bf4f3d4e20de9c6db6cb798dd1eb3a98da422a73cbf8da11e32b6a25dfef7","abstract_canon_sha256":"a7f7b7f65c6b53743d7429c219b326fd2dec812a86f5168364b2dfd805101881"},"schema_version":"1.0"},"canonical_sha256":"f9ad7d0b13acb65a56a8c79ac33073350b9a7d71b768c86110671ac8618fb570","source":{"kind":"arxiv","id":"2410.23179","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23179","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23179v2","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23179","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"7GWX2CYTVS3F","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"7GWX2CYTVS3FUVVI","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"7GWX2CYT","created_at":"2026-07-05T11:43:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7GWX2CYTVS3FUVVIY6NMGMDTGU","target":"record","payload":{"canonical_record":{"source":{"id":"2410.23179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T16:36:59Z","cross_cats_sorted":[],"title_canon_sha256":"858bf4f3d4e20de9c6db6cb798dd1eb3a98da422a73cbf8da11e32b6a25dfef7","abstract_canon_sha256":"a7f7b7f65c6b53743d7429c219b326fd2dec812a86f5168364b2dfd805101881"},"schema_version":"1.0"},"canonical_sha256":"f9ad7d0b13acb65a56a8c79ac33073350b9a7d71b768c86110671ac8618fb570","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:58.165264Z","signature_b64":"a4+NzecrGP+uyJVDVs2Aepf5GAAVwdciGluEXnMSo6PzgjbMTMtXvARcywcbS/Qt1414BwECaFAo2ToTEypqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9ad7d0b13acb65a56a8c79ac33073350b9a7d71b768c86110671ac8618fb570","last_reissued_at":"2026-07-05T11:43:58.164788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:58.164788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.23179","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"egJgrsUNgpBIEpAdrRDWxhtfCIRSMCOIkuGteQcKwKg3BNEmM8mTwjFy7KTec65wT52JYhf9cyBn0Ihi0YMwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:12:02.831892Z"},"content_sha256":"62d2c00e6046dfeb9b75077e55510331975730b7857b3d48193937dbc8d68b06","schema_version":"1.0","event_id":"sha256:62d2c00e6046dfeb9b75077e55510331975730b7857b3d48193937dbc8d68b06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7GWX2CYTVS3FUVVIY6NMGMDTGU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does equivariance matter at scale?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Johann Brehmer, Pim de Haan, S\\\"onke Behrends, Taco Cohen","submitted_at":"2024-10-30T16:36:59Z","abstract_excerpt":"Given large datasets and sufficient compute, is it beneficial to design neural architectures for the structure and symmetries of each problem? Or is it more efficient to learn them from data? We study empirically how equivariant and non-equivariant networks scale with compute and training samples. Focusing on a benchmark problem of rigid-body interactions and on general-purpose transformer architectures, we perform a series of experiments, varying the model size, training steps, and dataset size. We find evidence for three conclusions. First, equivariance improves data efficiency, but training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23179","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/2410.23179/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n9woZmn7+gu+JM+UdGJKeTcDCOFAxJB7nDWBOQky9SElYKBvyE2SdNnZUnaKCMhLNrReJN5cj9RVmia3JVwSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:12:02.832796Z"},"content_sha256":"7aa3ff1e789dd2b66dbf6d7aec5a840687a212b9ae971987d2672992c855111b","schema_version":"1.0","event_id":"sha256:7aa3ff1e789dd2b66dbf6d7aec5a840687a212b9ae971987d2672992c855111b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GWX2CYTVS3FUVVIY6NMGMDTGU/bundle.json","state_url":"https://pith.science/pith/7GWX2CYTVS3FUVVIY6NMGMDTGU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GWX2CYTVS3FUVVIY6NMGMDTGU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T00:12:02Z","links":{"resolver":"https://pith.science/pith/7GWX2CYTVS3FUVVIY6NMGMDTGU","bundle":"https://pith.science/pith/7GWX2CYTVS3FUVVIY6NMGMDTGU/bundle.json","state":"https://pith.science/pith/7GWX2CYTVS3FUVVIY6NMGMDTGU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GWX2CYTVS3FUVVIY6NMGMDTGU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7GWX2CYTVS3FUVVIY6NMGMDTGU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a7f7b7f65c6b53743d7429c219b326fd2dec812a86f5168364b2dfd805101881","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T16:36:59Z","title_canon_sha256":"858bf4f3d4e20de9c6db6cb798dd1eb3a98da422a73cbf8da11e32b6a25dfef7"},"schema_version":"1.0","source":{"id":"2410.23179","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23179","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23179v2","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23179","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"7GWX2CYTVS3F","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"7GWX2CYTVS3FUVVI","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"7GWX2CYT","created_at":"2026-07-05T11:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:7aa3ff1e789dd2b66dbf6d7aec5a840687a212b9ae971987d2672992c855111b","target":"graph","created_at":"2026-07-05T11:43:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.23179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given large datasets and sufficient compute, is it beneficial to design neural architectures for the structure and symmetries of each problem? Or is it more efficient to learn them from data? We study empirically how equivariant and non-equivariant networks scale with compute and training samples. Focusing on a benchmark problem of rigid-body interactions and on general-purpose transformer architectures, we perform a series of experiments, varying the model size, training steps, and dataset size. We find evidence for three conclusions. First, equivariance improves data efficiency, but training","authors_text":"Johann Brehmer, Pim de Haan, S\\\"onke Behrends, Taco Cohen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T16:36:59Z","title":"Does equivariance matter at scale?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23179","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:62d2c00e6046dfeb9b75077e55510331975730b7857b3d48193937dbc8d68b06","target":"record","created_at":"2026-07-05T11:43:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a7f7b7f65c6b53743d7429c219b326fd2dec812a86f5168364b2dfd805101881","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T16:36:59Z","title_canon_sha256":"858bf4f3d4e20de9c6db6cb798dd1eb3a98da422a73cbf8da11e32b6a25dfef7"},"schema_version":"1.0","source":{"id":"2410.23179","kind":"arxiv","version":2}},"canonical_sha256":"f9ad7d0b13acb65a56a8c79ac33073350b9a7d71b768c86110671ac8618fb570","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9ad7d0b13acb65a56a8c79ac33073350b9a7d71b768c86110671ac8618fb570","first_computed_at":"2026-07-05T11:43:58.164788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:58.164788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a4+NzecrGP+uyJVDVs2Aepf5GAAVwdciGluEXnMSo6PzgjbMTMtXvARcywcbS/Qt1414BwECaFAo2ToTEypqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:58.165264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23179","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62d2c00e6046dfeb9b75077e55510331975730b7857b3d48193937dbc8d68b06","sha256:7aa3ff1e789dd2b66dbf6d7aec5a840687a212b9ae971987d2672992c855111b"],"state_sha256":"083ae64df0c3e6a14192c458cc1a0474a7e20e25523ee98148ca035a9bdd3749"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RU+WW8lyvTYKmNfJD4VnLYeFeHKK5p7Vnby8znbQ1MTmYVmdcOkewvKuJJ5tfRsBxdeNG0Rih71QFaU9iaFWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:12:02.837656Z","bundle_sha256":"d4bf327809d2a0bd52c640f32dcd3897706319526e09273e0cf7e91428119e84"}}