{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U2DWKK5BQ3AALHBSTR2QIHMGWH","short_pith_number":"pith:U2DWKK5B","schema_version":"1.0","canonical_sha256":"a687652ba186c0059c329c75041d86b1d5a66e1049e224c0798872ba4969b9f2","source":{"kind":"arxiv","id":"2411.09816","version":4},"attestation_state":"computed","paper":{"title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cem \\\"Uy\\\"uk, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou","submitted_at":"2024-11-14T21:29:58Z","abstract_excerpt":"Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. Among existing compression approaches, cross-layer parameter sharing remains relatively unexplored for transformer models. In this paper, we introduce Fine-grained Parameter Sharing (FiPS), a unified framework for compressing transformer Multi-Layer Perceptrons (MLPs) that combines cross-block parameter sharing, low-rank factorization, and sparsity in a single optimization. FiPS concatenates MLP weight matrices across a group of transformer blocks a"},"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":"2411.09816","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T21:29:58Z","cross_cats_sorted":[],"title_canon_sha256":"9e519a3233ea6c1d5e15c1fedd2c3d4c3d81dd134d85d0185b52577faf9d7615","abstract_canon_sha256":"d04bbf5ab56c731722496f53eca9bb5c92f461be13d65a20b2199c9327b8ad63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:09.641090Z","signature_b64":"qWVbdk2RRxkdA2XLXEfMmDRNbF00oL06vYWxc55GpFQMibb6Gs75WwGRmmSAfQEDrSua8Zb6lvEtbmGgij70Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a687652ba186c0059c329c75041d86b1d5a66e1049e224c0798872ba4969b9f2","last_reissued_at":"2026-05-26T01:03:09.640206Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:09.640206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cem \\\"Uy\\\"uk, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou","submitted_at":"2024-11-14T21:29:58Z","abstract_excerpt":"Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. Among existing compression approaches, cross-layer parameter sharing remains relatively unexplored for transformer models. In this paper, we introduce Fine-grained Parameter Sharing (FiPS), a unified framework for compressing transformer Multi-Layer Perceptrons (MLPs) that combines cross-block parameter sharing, low-rank factorization, and sparsity in a single optimization. FiPS concatenates MLP weight matrices across a group of transformer blocks a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09816","kind":"arxiv","version":4},"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/2411.09816/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":"2411.09816","created_at":"2026-05-26T01:03:09.640343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09816v4","created_at":"2026-05-26T01:03:09.640343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09816","created_at":"2026-05-26T01:03:09.640343+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2DWKK5BQ3AA","created_at":"2026-05-26T01:03:09.640343+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2DWKK5BQ3AALHBS","created_at":"2026-05-26T01:03:09.640343+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2DWKK5B","created_at":"2026-05-26T01:03:09.640343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09428","citing_title":"On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization","ref_index":85,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH","json":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH.json","graph_json":"https://pith.science/api/pith-number/U2DWKK5BQ3AALHBSTR2QIHMGWH/graph.json","events_json":"https://pith.science/api/pith-number/U2DWKK5BQ3AALHBSTR2QIHMGWH/events.json","paper":"https://pith.science/paper/U2DWKK5B"},"agent_actions":{"view_html":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH","download_json":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH.json","view_paper":"https://pith.science/paper/U2DWKK5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09816&json=true","fetch_graph":"https://pith.science/api/pith-number/U2DWKK5BQ3AALHBSTR2QIHMGWH/graph.json","fetch_events":"https://pith.science/api/pith-number/U2DWKK5BQ3AALHBSTR2QIHMGWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/action/storage_attestation","attest_author":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/action/author_attestation","sign_citation":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/action/citation_signature","submit_replication":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/action/replication_record"}},"created_at":"2026-05-26T01:03:09.640343+00:00","updated_at":"2026-05-26T01:03:09.640343+00:00"}