{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ATCYYAFIVLDY6DDXJNHQXSQKZI","short_pith_number":"pith:ATCYYAFI","schema_version":"1.0","canonical_sha256":"04c58c00a8aac78f0c774b4f0bca0aca29583c6adf46c8a3cce5b4df1a549b92","source":{"kind":"arxiv","id":"1812.03928","version":3},"attestation_state":"computed","paper":{"title":"Learning Representations of Sets through Optimized Permutations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Pr\\\"ugel-Bennett, Jonathon Hare, Yan Zhang","submitted_at":"2018-12-10T17:26:25Z","abstract_excerpt":"Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns how to permute a set end-to-end. The permuted set can be further processed to learn a permutation-invariant representation of that set, avoiding a bottleneck in traditional set models. We demonstrate our model's ability to learn permutations and set representations with either explicit or implicit supervision on four datasets, on which we achieve state-of-the-art results: number sorting, image mosaics, classification "},"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":"1812.03928","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-10T17:26:25Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"c6388105f8ffcfb690dfc74d0cba31bead8704cfd69910dfdf8bab405ad5ca26","abstract_canon_sha256":"063514ade1ba94c01c95a0195b9690e204d9fb9d73c96cd6919c73ae1a9f3655"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:22.877968Z","signature_b64":"x4MwxtOznJjEoYcLrCsYDhIZBFaU/0qLUCj8gPhIlIa+BZ6RjQuOe0OP+ZhnhR9BE0jBT3tbgIPVtFTijEneCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04c58c00a8aac78f0c774b4f0bca0aca29583c6adf46c8a3cce5b4df1a549b92","last_reissued_at":"2026-05-17T23:56:22.877267Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:22.877267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Representations of Sets through Optimized Permutations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Pr\\\"ugel-Bennett, Jonathon Hare, Yan Zhang","submitted_at":"2018-12-10T17:26:25Z","abstract_excerpt":"Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns how to permute a set end-to-end. The permuted set can be further processed to learn a permutation-invariant representation of that set, avoiding a bottleneck in traditional set models. We demonstrate our model's ability to learn permutations and set representations with either explicit or implicit supervision on four datasets, on which we achieve state-of-the-art results: number sorting, image mosaics, classification "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03928","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1812.03928","created_at":"2026-05-17T23:56:22.877394+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03928v3","created_at":"2026-05-17T23:56:22.877394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03928","created_at":"2026-05-17T23:56:22.877394+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATCYYAFIVLDY","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATCYYAFIVLDY6DDX","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATCYYAFI","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.24886","citing_title":"Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI","json":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI.json","graph_json":"https://pith.science/api/pith-number/ATCYYAFIVLDY6DDXJNHQXSQKZI/graph.json","events_json":"https://pith.science/api/pith-number/ATCYYAFIVLDY6DDXJNHQXSQKZI/events.json","paper":"https://pith.science/paper/ATCYYAFI"},"agent_actions":{"view_html":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI","download_json":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI.json","view_paper":"https://pith.science/paper/ATCYYAFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03928&json=true","fetch_graph":"https://pith.science/api/pith-number/ATCYYAFIVLDY6DDXJNHQXSQKZI/graph.json","fetch_events":"https://pith.science/api/pith-number/ATCYYAFIVLDY6DDXJNHQXSQKZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI/action/storage_attestation","attest_author":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI/action/author_attestation","sign_citation":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI/action/citation_signature","submit_replication":"https://pith.science/pith/ATCYYAFIVLDY6DDXJNHQXSQKZI/action/replication_record"}},"created_at":"2026-05-17T23:56:22.877394+00:00","updated_at":"2026-05-17T23:56:22.877394+00:00"}