{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:APN5EPVHFHEU7HCUSMGUSXN3VX","short_pith_number":"pith:APN5EPVH","schema_version":"1.0","canonical_sha256":"03dbd23ea729c94f9c54930d495dbbadf869a24c96dc73c9a729cdeceb36c6fd","source":{"kind":"arxiv","id":"1901.06082","version":2},"attestation_state":"computed","paper":{"title":"Probabilistic symmetries and invariant neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Bloem-Reddy, Yee Whye Teh","submitted_at":"2019-01-18T04:32:14Z","abstract_excerpt":"Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has been devoted to encoding invariance under symmetry transformations into neural network architectures, in an effort to improve the performance of deep neural networks in data-scarce, non-i.i.d., or unsupervised settings. By considering group invariance from the perspective of probabilistic symmetry, we establish a link between functional and probabilistic sym"},"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":"1901.06082","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2019-01-18T04:32:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"615babf8b2b697a76167ab6d7ddc2570da5e91a3eab2e336e7a47e0c296e96e0","abstract_canon_sha256":"4450a1e125c51813fe53af1795cffcc6b1deeafe349522016860b03961221e8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:56.369435Z","signature_b64":"bmHrKTBI+1Aramh5XIwVPOBjJRm1HPTulMIfP1i+dsNvYHvqG4pNMkf7fkK60hVwKjAsWpndEyFap9EdOJmYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03dbd23ea729c94f9c54930d495dbbadf869a24c96dc73c9a729cdeceb36c6fd","last_reissued_at":"2026-07-05T01:35:56.368937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:56.368937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic symmetries and invariant neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Bloem-Reddy, Yee Whye Teh","submitted_at":"2019-01-18T04:32:14Z","abstract_excerpt":"Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has been devoted to encoding invariance under symmetry transformations into neural network architectures, in an effort to improve the performance of deep neural networks in data-scarce, non-i.i.d., or unsupervised settings. By considering group invariance from the perspective of probabilistic symmetry, we establish a link between functional and probabilistic sym"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.06082","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/1901.06082/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":"1901.06082","created_at":"2026-07-05T01:35:56.368996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.06082v2","created_at":"2026-07-05T01:35:56.368996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.06082","created_at":"2026-07-05T01:35:56.368996+00:00"},{"alias_kind":"pith_short_12","alias_value":"APN5EPVHFHEU","created_at":"2026-07-05T01:35:56.368996+00:00"},{"alias_kind":"pith_short_16","alias_value":"APN5EPVHFHEU7HCU","created_at":"2026-07-05T01:35:56.368996+00:00"},{"alias_kind":"pith_short_8","alias_value":"APN5EPVH","created_at":"2026-07-05T01:35:56.368996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31282","citing_title":"Revisiting the Volume Hypothesis","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09716","citing_title":"Medical Model Synthesis Architectures: A Case Study","ref_index":199,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX","json":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX.json","graph_json":"https://pith.science/api/pith-number/APN5EPVHFHEU7HCUSMGUSXN3VX/graph.json","events_json":"https://pith.science/api/pith-number/APN5EPVHFHEU7HCUSMGUSXN3VX/events.json","paper":"https://pith.science/paper/APN5EPVH"},"agent_actions":{"view_html":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX","download_json":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX.json","view_paper":"https://pith.science/paper/APN5EPVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.06082&json=true","fetch_graph":"https://pith.science/api/pith-number/APN5EPVHFHEU7HCUSMGUSXN3VX/graph.json","fetch_events":"https://pith.science/api/pith-number/APN5EPVHFHEU7HCUSMGUSXN3VX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX/action/storage_attestation","attest_author":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX/action/author_attestation","sign_citation":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX/action/citation_signature","submit_replication":"https://pith.science/pith/APN5EPVHFHEU7HCUSMGUSXN3VX/action/replication_record"}},"created_at":"2026-07-05T01:35:56.368996+00:00","updated_at":"2026-07-05T01:35:56.368996+00:00"}