{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VPKWH5JQ2MREU2X7RC7Y5P7I66","short_pith_number":"pith:VPKWH5JQ","schema_version":"1.0","canonical_sha256":"abd563f530d3224a6aff88bf8ebfe8f7aefbb6be5cf230850afac5e0d172594c","source":{"kind":"arxiv","id":"2102.08597","version":1},"attestation_state":"computed","paper":{"title":"Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alvin Chan, Anh Tuan Luu, Aston Zhang, Jie Fu, Shuai Zhang, Siu Cheung Hui, Yi Tay","submitted_at":"2021-02-17T06:16:58Z","abstract_excerpt":"Recent works have demonstrated reasonable success of representation learning in hypercomplex space. Specifically, \"fully-connected layers with Quaternions\" (4D hypercomplex numbers), which replace real-valued matrix multiplications in fully-connected layers with Hamilton products of Quaternions, both enjoy parameter savings with only 1/4 learnable parameters and achieve comparable performance in various applications. However, one key caveat is that hypercomplex space only exists at very few predefined dimensions (4D, 8D, and 16D). This restricts the flexibility of models that leverage hypercom"},"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":"2102.08597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T06:16:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"5f0ac8e401dce83bf6c751651de5312f75934b2ecc1a16c2696a4e2df9dee777","abstract_canon_sha256":"adf67ad9c580ce7792c26e3eb5f809dd2977fcf9d50c39ddc14b0ab7b6bf7619"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:04.989002Z","signature_b64":"ajnXW+2wZR3NRAG+Gra3Oy7Ti5Z5l/mF6nDcagelBB/II1z71iXaF5AR6AAkv/cd7ZEPpRw86VLzL7y/F06tAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abd563f530d3224a6aff88bf8ebfe8f7aefbb6be5cf230850afac5e0d172594c","last_reissued_at":"2026-07-05T02:16:04.988566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:04.988566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alvin Chan, Anh Tuan Luu, Aston Zhang, Jie Fu, Shuai Zhang, Siu Cheung Hui, Yi Tay","submitted_at":"2021-02-17T06:16:58Z","abstract_excerpt":"Recent works have demonstrated reasonable success of representation learning in hypercomplex space. Specifically, \"fully-connected layers with Quaternions\" (4D hypercomplex numbers), which replace real-valued matrix multiplications in fully-connected layers with Hamilton products of Quaternions, both enjoy parameter savings with only 1/4 learnable parameters and achieve comparable performance in various applications. However, one key caveat is that hypercomplex space only exists at very few predefined dimensions (4D, 8D, and 16D). This restricts the flexibility of models that leverage hypercom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08597","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/2102.08597/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":"2102.08597","created_at":"2026-07-05T02:16:04.988632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08597v1","created_at":"2026-07-05T02:16:04.988632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08597","created_at":"2026-07-05T02:16:04.988632+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPKWH5JQ2MRE","created_at":"2026-07-05T02:16:04.988632+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPKWH5JQ2MREU2X7","created_at":"2026-07-05T02:16:04.988632+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPKWH5JQ","created_at":"2026-07-05T02:16:04.988632+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/VPKWH5JQ2MREU2X7RC7Y5P7I66","json":"https://pith.science/pith/VPKWH5JQ2MREU2X7RC7Y5P7I66.json","graph_json":"https://pith.science/api/pith-number/VPKWH5JQ2MREU2X7RC7Y5P7I66/graph.json","events_json":"https://pith.science/api/pith-number/VPKWH5JQ2MREU2X7RC7Y5P7I66/events.json","paper":"https://pith.science/paper/VPKWH5JQ"},"agent_actions":{"view_html":"https://pith.science/pith/VPKWH5JQ2MREU2X7RC7Y5P7I66","download_json":"https://pith.science/pith/VPKWH5JQ2MREU2X7RC7Y5P7I66.json","view_paper":"https://pith.science/paper/VPKWH5JQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08597&json=true","fetch_graph":"https://pith.science/api/pith-number/VPKWH5JQ2MREU2X7RC7Y5P7I66/graph.json","fetch_events":"https://pith.science/api/pith-number/VPKWH5JQ2MREU2X7RC7Y5P7I66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPKWH5JQ2MREU2X7RC7Y5P7I66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPKWH5JQ2MREU2X7RC7Y5P7I66/action/storage_attestation","attest_author":"https://pith.science/pith/VPKWH5JQ2MREU2X7RC7Y5P7I66/action/author_attestation","sign_citation":"https://pith.science/pith/VPKWH5JQ2MREU2X7RC7Y5P7I66/action/citation_signature","submit_replication":"https://pith.science/pith/VPKWH5JQ2MREU2X7RC7Y5P7I66/action/replication_record"}},"created_at":"2026-07-05T02:16:04.988632+00:00","updated_at":"2026-07-05T02:16:04.988632+00:00"}