{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WXYKFM4WKNL5QWZ5OSIXSAHKM6","short_pith_number":"pith:WXYKFM4W","schema_version":"1.0","canonical_sha256":"b5f0a2b3965357d85b3d74917900ea67b2a08311ca9434323eaa779f5baa4e57","source":{"kind":"arxiv","id":"2203.07546","version":1},"attestation_state":"computed","paper":{"title":"Permutation Invariant Representations with Applications to Graph Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.FA","authors_text":"Maneesh Singh, Naveed Haghani, Radu Balan","submitted_at":"2022-03-14T23:13:59Z","abstract_excerpt":"This paper presents primarily two Euclidean embeddings of the quotient space generated by matrices that are identified modulo arbitrary row permutations. The original application is in deep learning on graphs where the learning task is invariant to node relabeling. Two embedding schemes are introduced, one based on sorting and the other based on algebras of multivariate polynomials. While both embeddings exhibit a computational complexity exponential in problem size, the sorting based embedding is globally bi-Lipschitz and admits a low dimensional target space. Additionally, an almost everywhe"},"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":"2203.07546","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.FA","submitted_at":"2022-03-14T23:13:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df5f2dc7345f9e5d6c9a832d73e7c2165fc39efa2cf09479dd4cae8c5a3d3306","abstract_canon_sha256":"19ac8e490a2368ebc3d6b29a4150b93ccc1ac58da95491afcf66aae99370b937"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:19.640107Z","signature_b64":"Dooyy1K+L/liIM4hdYc3NnD6su1fYYLtbTUTT1/xpU/u9yttAibqhljT+DdpnKivMPDq9njWDZQCsrw1d8u1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5f0a2b3965357d85b3d74917900ea67b2a08311ca9434323eaa779f5baa4e57","last_reissued_at":"2026-07-05T04:05:19.639642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:19.639642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Permutation Invariant Representations with Applications to Graph Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.FA","authors_text":"Maneesh Singh, Naveed Haghani, Radu Balan","submitted_at":"2022-03-14T23:13:59Z","abstract_excerpt":"This paper presents primarily two Euclidean embeddings of the quotient space generated by matrices that are identified modulo arbitrary row permutations. The original application is in deep learning on graphs where the learning task is invariant to node relabeling. Two embedding schemes are introduced, one based on sorting and the other based on algebras of multivariate polynomials. While both embeddings exhibit a computational complexity exponential in problem size, the sorting based embedding is globally bi-Lipschitz and admits a low dimensional target space. Additionally, an almost everywhe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07546","kind":"arxiv","version":1},"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/2203.07546/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":"2203.07546","created_at":"2026-07-05T04:05:19.639713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07546v1","created_at":"2026-07-05T04:05:19.639713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07546","created_at":"2026-07-05T04:05:19.639713+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXYKFM4WKNL5","created_at":"2026-07-05T04:05:19.639713+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXYKFM4WKNL5QWZ5","created_at":"2026-07-05T04:05:19.639713+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXYKFM4W","created_at":"2026-07-05T04:05:19.639713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.23634","citing_title":"Monotone and Separable Set Functions: Characterizations and Neural Models","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6","json":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6.json","graph_json":"https://pith.science/api/pith-number/WXYKFM4WKNL5QWZ5OSIXSAHKM6/graph.json","events_json":"https://pith.science/api/pith-number/WXYKFM4WKNL5QWZ5OSIXSAHKM6/events.json","paper":"https://pith.science/paper/WXYKFM4W"},"agent_actions":{"view_html":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6","download_json":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6.json","view_paper":"https://pith.science/paper/WXYKFM4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07546&json=true","fetch_graph":"https://pith.science/api/pith-number/WXYKFM4WKNL5QWZ5OSIXSAHKM6/graph.json","fetch_events":"https://pith.science/api/pith-number/WXYKFM4WKNL5QWZ5OSIXSAHKM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6/action/storage_attestation","attest_author":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6/action/author_attestation","sign_citation":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6/action/citation_signature","submit_replication":"https://pith.science/pith/WXYKFM4WKNL5QWZ5OSIXSAHKM6/action/replication_record"}},"created_at":"2026-07-05T04:05:19.639713+00:00","updated_at":"2026-07-05T04:05:19.639713+00:00"}