{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RPMZX5FTVEADH2LK53XUOOWGBZ","short_pith_number":"pith:RPMZX5FT","schema_version":"1.0","canonical_sha256":"8bd99bf4b3a90033e96aeeef473ac60e5607823dcbdbad70c3564d12b96dfceb","source":{"kind":"arxiv","id":"2602.00942","version":3},"attestation_state":"computed","paper":{"title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingcong Li, Hao Ma, Liang Zhang, Melanie Zeilinger, Melis Ilayda Bal, Michael Muehlebach, Niao He","submitted_at":"2026-02-01T00:00:11Z","abstract_excerpt":"Modern large language models are increasingly deployed under compute and memory constraints, making flexible control of model capacity a central challenge. While sparse and low-rank structures naturally trade off capacity and performance, existing approaches often rely on heuristic designs that ignore layer and matrix heterogeneity or require model-specific architectural modifications. We propose SALAAD, a plug-and-play framework applicable to different model architectures that induces sparse and low-rank structures during training. By formulating structured weight learning under an augmented "},"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":"2602.00942","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-01T00:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"65e4c1a3368a5675b74cc998189c946b71b2c9b22ad029221cef979bc7224de7","abstract_canon_sha256":"b00504bce8b2e73b0f8f405de11e01beb85369882828e1bd31574f9fd06388e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:31.132688Z","signature_b64":"viGDnF6pmqntXQC0/vzFnw5wPmydJOKzx/CJ9Y2CLoQMLzSxTbz7xrrDNpddkFkgdUBd3Z21znQ2Whdp6DMwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bd99bf4b3a90033e96aeeef473ac60e5607823dcbdbad70c3564d12b96dfceb","last_reissued_at":"2026-06-01T01:02:31.131861Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:31.131861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingcong Li, Hao Ma, Liang Zhang, Melanie Zeilinger, Melis Ilayda Bal, Michael Muehlebach, Niao He","submitted_at":"2026-02-01T00:00:11Z","abstract_excerpt":"Modern large language models are increasingly deployed under compute and memory constraints, making flexible control of model capacity a central challenge. While sparse and low-rank structures naturally trade off capacity and performance, existing approaches often rely on heuristic designs that ignore layer and matrix heterogeneity or require model-specific architectural modifications. We propose SALAAD, a plug-and-play framework applicable to different model architectures that induces sparse and low-rank structures during training. By formulating structured weight learning under an augmented "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00942","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.00942/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":"2602.00942","created_at":"2026-06-01T01:02:31.131983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.00942v3","created_at":"2026-06-01T01:02:31.131983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00942","created_at":"2026-06-01T01:02:31.131983+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPMZX5FTVEAD","created_at":"2026-06-01T01:02:31.131983+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPMZX5FTVEADH2LK","created_at":"2026-06-01T01:02:31.131983+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPMZX5FT","created_at":"2026-06-01T01:02:31.131983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.21905","citing_title":"Low-Rank Adaptation Redux for Large Models","ref_index":125,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ","json":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ.json","graph_json":"https://pith.science/api/pith-number/RPMZX5FTVEADH2LK53XUOOWGBZ/graph.json","events_json":"https://pith.science/api/pith-number/RPMZX5FTVEADH2LK53XUOOWGBZ/events.json","paper":"https://pith.science/paper/RPMZX5FT"},"agent_actions":{"view_html":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ","download_json":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ.json","view_paper":"https://pith.science/paper/RPMZX5FT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.00942&json=true","fetch_graph":"https://pith.science/api/pith-number/RPMZX5FTVEADH2LK53XUOOWGBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RPMZX5FTVEADH2LK53XUOOWGBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ/action/storage_attestation","attest_author":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ/action/author_attestation","sign_citation":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ/action/citation_signature","submit_replication":"https://pith.science/pith/RPMZX5FTVEADH2LK53XUOOWGBZ/action/replication_record"}},"created_at":"2026-06-01T01:02:31.131983+00:00","updated_at":"2026-06-01T01:02:31.131983+00:00"}