{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O7YH4I7FF7UE2PQV5DUEAJHJXN","short_pith_number":"pith:O7YH4I7F","schema_version":"1.0","canonical_sha256":"77f07e23e52fe84d3e15e8e84024e9bb7a5fd63b916ed6100f3bcf1135e86467","source":{"kind":"arxiv","id":"2207.07743","version":1},"attestation_state":"computed","paper":{"title":"HOME: High-Order Mixed-Moment-based Embedding for Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chuang Niu, Ge Wang","submitted_at":"2022-07-15T20:34:49Z","abstract_excerpt":"Minimum redundancy among different elements of an embedding in a latent space is a fundamental requirement or major preference in representation learning to capture intrinsic informational structures. Current self-supervised learning methods minimize a pair-wise covariance matrix to reduce the feature redundancy and produce promising results. However, such representation features of multiple variables may contain the redundancy among more than two feature variables that cannot be minimized via the pairwise regularization. Here we propose the High-Order Mixed-Moment-based Embedding (HOME) strat"},"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":"2207.07743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-15T20:34:49Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"24ad86ddef77982c0685218fb7cbe9740960e35fd91a17e8e80a2354c4d15131","abstract_canon_sha256":"f7dc8f36b1da27cf1b3ea990600a7133f353c45622ee2602963d5af3ff572096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:36.580008Z","signature_b64":"zMXOeRpV1J7VKq0G8cVzS8X+3vk9LjLbkc9ePsFnvzwG7Ffkb96Up1oEDtHk1trCA+a/hbs9zSbGQqP5pW8LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77f07e23e52fe84d3e15e8e84024e9bb7a5fd63b916ed6100f3bcf1135e86467","last_reissued_at":"2026-07-05T04:40:36.579625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:36.579625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOME: High-Order Mixed-Moment-based Embedding for Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chuang Niu, Ge Wang","submitted_at":"2022-07-15T20:34:49Z","abstract_excerpt":"Minimum redundancy among different elements of an embedding in a latent space is a fundamental requirement or major preference in representation learning to capture intrinsic informational structures. Current self-supervised learning methods minimize a pair-wise covariance matrix to reduce the feature redundancy and produce promising results. However, such representation features of multiple variables may contain the redundancy among more than two feature variables that cannot be minimized via the pairwise regularization. Here we propose the High-Order Mixed-Moment-based Embedding (HOME) strat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07743","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/2207.07743/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":"2207.07743","created_at":"2026-07-05T04:40:36.579672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.07743v1","created_at":"2026-07-05T04:40:36.579672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07743","created_at":"2026-07-05T04:40:36.579672+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7YH4I7FF7UE","created_at":"2026-07-05T04:40:36.579672+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7YH4I7FF7UE2PQV","created_at":"2026-07-05T04:40:36.579672+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7YH4I7F","created_at":"2026-07-05T04:40:36.579672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN","json":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN.json","graph_json":"https://pith.science/api/pith-number/O7YH4I7FF7UE2PQV5DUEAJHJXN/graph.json","events_json":"https://pith.science/api/pith-number/O7YH4I7FF7UE2PQV5DUEAJHJXN/events.json","paper":"https://pith.science/paper/O7YH4I7F"},"agent_actions":{"view_html":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN","download_json":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN.json","view_paper":"https://pith.science/paper/O7YH4I7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.07743&json=true","fetch_graph":"https://pith.science/api/pith-number/O7YH4I7FF7UE2PQV5DUEAJHJXN/graph.json","fetch_events":"https://pith.science/api/pith-number/O7YH4I7FF7UE2PQV5DUEAJHJXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN/action/storage_attestation","attest_author":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN/action/author_attestation","sign_citation":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN/action/citation_signature","submit_replication":"https://pith.science/pith/O7YH4I7FF7UE2PQV5DUEAJHJXN/action/replication_record"}},"created_at":"2026-07-05T04:40:36.579672+00:00","updated_at":"2026-07-05T04:40:36.579672+00:00"}