{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MMWKDGG4BEXPWIY5KER73ZCN5O","short_pith_number":"pith:MMWKDGG4","schema_version":"1.0","canonical_sha256":"632ca198dc092efb231d5123fde44deb87c3ab9d03f0f6ce7b50b4a0c470914d","source":{"kind":"arxiv","id":"2403.17410","version":2},"attestation_state":"computed","paper":{"title":"On permutation-invariant neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masanari Kimura, Ryosuke Goto, Ryotaro Shimizu, Yuki Hirakawa, Yuki Saito","submitted_at":"2024-03-26T06:06:01Z","abstract_excerpt":"Conventional machine learning algorithms have traditionally been designed under the assumption that input data follows a vector-based format, with an emphasis on vector-centric paradigms. However, as the demand for tasks involving set-based inputs has grown, there has been a paradigm shift in the research community towards addressing these challenges. In recent years, the emergence of neural network architectures such as Deep Sets and Transformers has presented a significant advancement in the treatment of set-based data. These architectures are specifically engineered to naturally accommodate"},"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":"2403.17410","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-26T06:06:01Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"09b71799a9adc534409278c3f93df3a4531086c8bd04190c6529a1b68490ee32","abstract_canon_sha256":"fbdf9a4b6e1757c98f2ee7b4d15c532deff62af22298995a00120cd2c57523c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:06.511470Z","signature_b64":"FVISScWjBc33NtdiEFlnCKs140l/5lyxGGBQCi9XhUIS+3gk+jpJFhJOqo2iQUxKWuWNg7EqIgxtPAY/LtmsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"632ca198dc092efb231d5123fde44deb87c3ab9d03f0f6ce7b50b4a0c470914d","last_reissued_at":"2026-07-05T08:02:06.511020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:06.511020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On permutation-invariant neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masanari Kimura, Ryosuke Goto, Ryotaro Shimizu, Yuki Hirakawa, Yuki Saito","submitted_at":"2024-03-26T06:06:01Z","abstract_excerpt":"Conventional machine learning algorithms have traditionally been designed under the assumption that input data follows a vector-based format, with an emphasis on vector-centric paradigms. However, as the demand for tasks involving set-based inputs has grown, there has been a paradigm shift in the research community towards addressing these challenges. In recent years, the emergence of neural network architectures such as Deep Sets and Transformers has presented a significant advancement in the treatment of set-based data. These architectures are specifically engineered to naturally accommodate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17410","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/2403.17410/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":"2403.17410","created_at":"2026-07-05T08:02:06.511097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17410v2","created_at":"2026-07-05T08:02:06.511097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17410","created_at":"2026-07-05T08:02:06.511097+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMWKDGG4BEXP","created_at":"2026-07-05T08:02:06.511097+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMWKDGG4BEXPWIY5","created_at":"2026-07-05T08:02:06.511097+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMWKDGG4","created_at":"2026-07-05T08:02:06.511097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31500","citing_title":"On Efficient Scaling of GNNs via IO-Aware Layers Implementations","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27439","citing_title":"Simulation-Based Inference for Cluster Cosmology with Set-Based Neural Network Architectures","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02409","citing_title":"Inducing Permutation Invariant Priors in Bayesian Optimization for Carbon Capture and Storage Applications","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12021","citing_title":"What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02409","citing_title":"Inducing Permutation Invariant Priors in Bayesian Optimization for Carbon Capture and Storage Applications","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O","json":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O.json","graph_json":"https://pith.science/api/pith-number/MMWKDGG4BEXPWIY5KER73ZCN5O/graph.json","events_json":"https://pith.science/api/pith-number/MMWKDGG4BEXPWIY5KER73ZCN5O/events.json","paper":"https://pith.science/paper/MMWKDGG4"},"agent_actions":{"view_html":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O","download_json":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O.json","view_paper":"https://pith.science/paper/MMWKDGG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17410&json=true","fetch_graph":"https://pith.science/api/pith-number/MMWKDGG4BEXPWIY5KER73ZCN5O/graph.json","fetch_events":"https://pith.science/api/pith-number/MMWKDGG4BEXPWIY5KER73ZCN5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O/action/storage_attestation","attest_author":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O/action/author_attestation","sign_citation":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O/action/citation_signature","submit_replication":"https://pith.science/pith/MMWKDGG4BEXPWIY5KER73ZCN5O/action/replication_record"}},"created_at":"2026-07-05T08:02:06.511097+00:00","updated_at":"2026-07-05T08:02:06.511097+00:00"}