{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJT6UXTZEUVTXJQA5K5VV5E2YX","short_pith_number":"pith:BJT6UXTZ","schema_version":"1.0","canonical_sha256":"0a67ea5e79252b3ba600eabb5af49ac5e79e8a8baf1e02d7d72d63202bf36002","source":{"kind":"arxiv","id":"2403.08854","version":2},"attestation_state":"computed","paper":{"title":"Moments of Clarity: Streamlining Latent Spaces in Machine Learning using Moment Pooling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"hep-ph","authors_text":"Athis Osathapan, Jesse Thaler, Rikab Gambhir","submitted_at":"2024-03-13T18:00:01Z","abstract_excerpt":"Many machine learning applications involve learning a latent representation of data, which is often high-dimensional and difficult to directly interpret. In this work, we propose \"Moment Pooling\", a natural extension of Deep Sets networks which drastically decrease latent space dimensionality of these networks while maintaining or even improving performance. Moment Pooling generalizes the summation in Deep Sets to arbitrary multivariate moments, which enables the model to achieve a much higher effective latent dimensionality for a fixed latent dimension. We demonstrate Moment Pooling on the co"},"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":"2403.08854","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-ph","submitted_at":"2024-03-13T18:00:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"217377d035331eae07a783da309ecd653215533f427c9800ad55850f7e1a6c12","abstract_canon_sha256":"6cb9e9a9711764183d85986c398c5f1204636ebc05cdeb8685a835b0e07cfc0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:42.106861Z","signature_b64":"Od9IC06/1HsvmKDxVkuRPxYVMtGKsDu1CgqAZ+9PTTkS4Di9KBGs7o/5lJJ5JC2kLur0E1IBBKw0NxPW9ziDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a67ea5e79252b3ba600eabb5af49ac5e79e8a8baf1e02d7d72d63202bf36002","last_reissued_at":"2026-07-05T09:21:42.106400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:42.106400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moments of Clarity: Streamlining Latent Spaces in Machine Learning using Moment Pooling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"hep-ph","authors_text":"Athis Osathapan, Jesse Thaler, Rikab Gambhir","submitted_at":"2024-03-13T18:00:01Z","abstract_excerpt":"Many machine learning applications involve learning a latent representation of data, which is often high-dimensional and difficult to directly interpret. In this work, we propose \"Moment Pooling\", a natural extension of Deep Sets networks which drastically decrease latent space dimensionality of these networks while maintaining or even improving performance. Moment Pooling generalizes the summation in Deep Sets to arbitrary multivariate moments, which enables the model to achieve a much higher effective latent dimensionality for a fixed latent dimension. We demonstrate Moment Pooling on the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08854","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/2403.08854/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":"2403.08854","created_at":"2026-07-05T09:21:42.106459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08854v2","created_at":"2026-07-05T09:21:42.106459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08854","created_at":"2026-07-05T09:21:42.106459+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJT6UXTZEUVT","created_at":"2026-07-05T09:21:42.106459+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJT6UXTZEUVTXJQA","created_at":"2026-07-05T09:21:42.106459+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJT6UXTZ","created_at":"2026-07-05T09:21:42.106459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09544","citing_title":"Explainable AI-assisted Optimization for Feynman Integral Reduction","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX","json":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX.json","graph_json":"https://pith.science/api/pith-number/BJT6UXTZEUVTXJQA5K5VV5E2YX/graph.json","events_json":"https://pith.science/api/pith-number/BJT6UXTZEUVTXJQA5K5VV5E2YX/events.json","paper":"https://pith.science/paper/BJT6UXTZ"},"agent_actions":{"view_html":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX","download_json":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX.json","view_paper":"https://pith.science/paper/BJT6UXTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08854&json=true","fetch_graph":"https://pith.science/api/pith-number/BJT6UXTZEUVTXJQA5K5VV5E2YX/graph.json","fetch_events":"https://pith.science/api/pith-number/BJT6UXTZEUVTXJQA5K5VV5E2YX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX/action/storage_attestation","attest_author":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX/action/author_attestation","sign_citation":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX/action/citation_signature","submit_replication":"https://pith.science/pith/BJT6UXTZEUVTXJQA5K5VV5E2YX/action/replication_record"}},"created_at":"2026-07-05T09:21:42.106459+00:00","updated_at":"2026-07-05T09:21:42.106459+00:00"}