{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TVNBXLHNCU52FTPFWPAPXFXBOU","short_pith_number":"pith:TVNBXLHN","schema_version":"1.0","canonical_sha256":"9d5a1baced153ba2cde5b3c0fb96e175237126428b97b2c29137f7aa97cc3218","source":{"kind":"arxiv","id":"1703.06114","version":3},"attestation_state":"computed","paper":{"title":"Deep Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Smola, Barnabas Poczos, Manzil Zaheer, Ruslan Salakhutdinov, Satwik Kottur, Siamak Ravanbakhsh","submitted_at":"2017-03-10T21:02:53Z","abstract_excerpt":"We study the problem of designing models for machine learning tasks defined on \\emph{sets}. In contrast to traditional approach of operating on fixed dimensional vectors, we consider objective functions defined on sets that are invariant to permutations. Such problems are widespread, ranging from estimation of population statistics \\cite{poczos13aistats}, to anomaly detection in piezometer data of embankment dams \\cite{Jung15Exploration}, to cosmology \\cite{Ntampaka16Dynamical,Ravanbakhsh16ICML1}. Our main theorem characterizes the permutation invariant functions and provides a family of funct"},"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":"1703.06114","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-10T21:02:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"81ee3abfa96037fe29a6b063587056cf7d26ed8be329c55c6baba3e473d99e32","abstract_canon_sha256":"e883d0260b319ec21b1bdc23ff7d0313a8c5d6853c1f035c3377c70412a16f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:31.924582Z","signature_b64":"IiksRWdG8Se53zQNNxp9lrTAewQrorXQDmq5iMsJLtKsfisOZrnWheoUP0GUpvzQy2iGvc2c6pQuXPjto4DmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d5a1baced153ba2cde5b3c0fb96e175237126428b97b2c29137f7aa97cc3218","last_reissued_at":"2026-05-18T00:18:31.924205Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:31.924205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Smola, Barnabas Poczos, Manzil Zaheer, Ruslan Salakhutdinov, Satwik Kottur, Siamak Ravanbakhsh","submitted_at":"2017-03-10T21:02:53Z","abstract_excerpt":"We study the problem of designing models for machine learning tasks defined on \\emph{sets}. In contrast to traditional approach of operating on fixed dimensional vectors, we consider objective functions defined on sets that are invariant to permutations. Such problems are widespread, ranging from estimation of population statistics \\cite{poczos13aistats}, to anomaly detection in piezometer data of embankment dams \\cite{Jung15Exploration}, to cosmology \\cite{Ntampaka16Dynamical,Ravanbakhsh16ICML1}. Our main theorem characterizes the permutation invariant functions and provides a family of funct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06114","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":"1703.06114","created_at":"2026-05-18T00:18:31.924266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.06114v3","created_at":"2026-05-18T00:18:31.924266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06114","created_at":"2026-05-18T00:18:31.924266+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVNBXLHNCU52","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVNBXLHNCU52FTPF","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVNBXLHN","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":15,"sample":[{"citing_arxiv_id":"2412.19952","citing_title":"First evidence for mixing-induced $CP$ violation in B$^0_\\mathrm{s}$ $\\to$ J/$\\psi\\,\\phi$(1020) decays in pp collisions at $\\sqrt{s} = $ 13 TeV","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2404.06335","citing_title":"Software and computing for Run 3 of the ATLAS experiment at the LHC","ref_index":228,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21789","citing_title":"Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.23634","citing_title":"Monotone and Separable Set Functions: Characterizations and Neural Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2510.23641","citing_title":"Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2512.09673","citing_title":"Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21483","citing_title":"Velocityformer: Broken-Symmetry-Matched Equivariant Graph Transformers for Cosmological Velocity Reconstruction","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16756","citing_title":"Higgs Physics with the XFEL Compton $\\boldsymbol{\\gamma\\gamma}$ Collider Concept at $\\boldsymbol{\\sqrt{s}=125}$ GeV","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2509.06484","citing_title":"Thermodynamically consistent machine learning model for excess Gibbs energy","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2510.12916","citing_title":"Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2512.23748","citing_title":"A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2601.02508","citing_title":"Fermi Sets: Universal and interpretable neural architectures for fermions","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2601.12659","citing_title":"Two-Layer Reinforcement Learning-Assisted Joint Beamforming and Trajectory Optimization for Multi-UAV Downlink Communications","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11019","citing_title":"Signal Decomposition Reveals Structure in Insider Threat Detection under Sparse Temporal Data","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27351","citing_title":"Modeling isotropic polyconvex hyperelasticity by neural networks -- sufficient and necessary criteria for compressible and incompressible materials","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07972","citing_title":"It Just Takes Two: Scaling Amortized Inference to Large Sets","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06458","citing_title":"Diffusion-Based Point-Cloud Generation of Heavy-Ion Events","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20723","citing_title":"Tokenised Flow Matching for Hierarchical Simulation Based Inference","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20156","citing_title":"Temporally Extended Mixture-of-Experts Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03745","citing_title":"The LHCb Experiment","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU","json":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU.json","graph_json":"https://pith.science/api/pith-number/TVNBXLHNCU52FTPFWPAPXFXBOU/graph.json","events_json":"https://pith.science/api/pith-number/TVNBXLHNCU52FTPFWPAPXFXBOU/events.json","paper":"https://pith.science/paper/TVNBXLHN"},"agent_actions":{"view_html":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU","download_json":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU.json","view_paper":"https://pith.science/paper/TVNBXLHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.06114&json=true","fetch_graph":"https://pith.science/api/pith-number/TVNBXLHNCU52FTPFWPAPXFXBOU/graph.json","fetch_events":"https://pith.science/api/pith-number/TVNBXLHNCU52FTPFWPAPXFXBOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU/action/storage_attestation","attest_author":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU/action/author_attestation","sign_citation":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU/action/citation_signature","submit_replication":"https://pith.science/pith/TVNBXLHNCU52FTPFWPAPXFXBOU/action/replication_record"}},"created_at":"2026-05-18T00:18:31.924266+00:00","updated_at":"2026-05-18T00:18:31.924266+00:00"}