{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C4GUFSU3HAKAHPNAVLFDQG7RJM","short_pith_number":"pith:C4GUFSU3","schema_version":"1.0","canonical_sha256":"170d42ca9b381403bda0aaca381bf14b08f1e2f1a9992578893594a0e1f811c0","source":{"kind":"arxiv","id":"2106.06610","version":4},"attestation_state":"computed","paper":{"title":"Scalars are universal: Equivariant machine learning, structured like classical physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math-ph","math.MP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Blum-Smith (NYU), David W. Hogg (Flatiron, Kate Storey-Fisher (NYU), NYU), Soledad Villar (JHU), Weichi Yao (NYU)","submitted_at":"2021-06-11T20:51:38Z","abstract_excerpt":"There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible representations, some make use of high-order tensor objects, and some apply symmetry-enforcing constraints. Different physical laws obey different combinations of fundamental symmetries, but a large fraction (possibly all) of classical physics is equivariant to translation, rotation, reflection (parity), boost (relativity), and permutations. Here we show that it is simple to paramete"},"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":"2106.06610","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T20:51:38Z","cross_cats_sorted":["math-ph","math.MP","stat.ML"],"title_canon_sha256":"3b69c3f7ecd170e4de6b1d88bf8ce6a9c0bec7910df29e50dce7c922e8ea59f1","abstract_canon_sha256":"427bf3f8737a473117ed44f80af63069035ab99a5b5efbcdf84a2f5e9f9e4317"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:49.163978Z","signature_b64":"3zuigjf07hwe3TmBSuY+t9uWPT69NdjVb1u+THS8XUwF7/K9rDqOCxuVnG8Lamh9ygHwTCI/q3L7xHgrpWHhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"170d42ca9b381403bda0aaca381bf14b08f1e2f1a9992578893594a0e1f811c0","last_reissued_at":"2026-07-05T05:39:49.163519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:49.163519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalars are universal: Equivariant machine learning, structured like classical physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math-ph","math.MP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Blum-Smith (NYU), David W. Hogg (Flatiron, Kate Storey-Fisher (NYU), NYU), Soledad Villar (JHU), Weichi Yao (NYU)","submitted_at":"2021-06-11T20:51:38Z","abstract_excerpt":"There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible representations, some make use of high-order tensor objects, and some apply symmetry-enforcing constraints. Different physical laws obey different combinations of fundamental symmetries, but a large fraction (possibly all) of classical physics is equivariant to translation, rotation, reflection (parity), boost (relativity), and permutations. Here we show that it is simple to paramete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06610","kind":"arxiv","version":4},"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/2106.06610/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":"2106.06610","created_at":"2026-07-05T05:39:49.163578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06610v4","created_at":"2026-07-05T05:39:49.163578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06610","created_at":"2026-07-05T05:39:49.163578+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4GUFSU3HAKA","created_at":"2026-07-05T05:39:49.163578+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4GUFSU3HAKAHPNA","created_at":"2026-07-05T05:39:49.163578+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4GUFSU3","created_at":"2026-07-05T05:39:49.163578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10038","citing_title":"Learning the Universe with the 2nd Generation of CAMELS: Varying 35 parameters of the IllustrisTNG model in (50Mpc/h)^3 boxes","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM","json":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM.json","graph_json":"https://pith.science/api/pith-number/C4GUFSU3HAKAHPNAVLFDQG7RJM/graph.json","events_json":"https://pith.science/api/pith-number/C4GUFSU3HAKAHPNAVLFDQG7RJM/events.json","paper":"https://pith.science/paper/C4GUFSU3"},"agent_actions":{"view_html":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM","download_json":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM.json","view_paper":"https://pith.science/paper/C4GUFSU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06610&json=true","fetch_graph":"https://pith.science/api/pith-number/C4GUFSU3HAKAHPNAVLFDQG7RJM/graph.json","fetch_events":"https://pith.science/api/pith-number/C4GUFSU3HAKAHPNAVLFDQG7RJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM/action/storage_attestation","attest_author":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM/action/author_attestation","sign_citation":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM/action/citation_signature","submit_replication":"https://pith.science/pith/C4GUFSU3HAKAHPNAVLFDQG7RJM/action/replication_record"}},"created_at":"2026-07-05T05:39:49.163578+00:00","updated_at":"2026-07-05T05:39:49.163578+00:00"}