{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CQ4VVR5UPLX5BL5ZXBFR2CICJJ","short_pith_number":"pith:CQ4VVR5U","schema_version":"1.0","canonical_sha256":"14395ac7b47aefd0afb9b84b1d09024a6b1ec0535b8239c8eff7fc7788cb9cd4","source":{"kind":"arxiv","id":"2205.12410","version":2},"attestation_state":"computed","paper":{"title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Hassan Awadallah, Jianfeng Gao, Jing Gao, Sahaj Agarwal, Subhabrata Mukherjee, XiaoDong Liu, Yaqing Wang","submitted_at":"2022-05-24T23:41:22Z","abstract_excerpt":"Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models. To address this, parameter-efficient fine-tuning (PEFT) techniques were introduced where small trainable components are injected in the PLM and updated during fine-tuning. We propose AdaMix as a general PEFT method that tunes a mixture of adaptation modules -- given the underlying PEFT method of choice -- introduce"},"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":"2205.12410","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T23:41:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0271ca7fd3f49b5b6e4c4e6a49528473db3d9325e5fe58cfab2a2efb5c9b2800","abstract_canon_sha256":"0543650958ae285e6a9a058a33fede91ab832b978bda222d75901e4f2b3914f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:07.001113Z","signature_b64":"e/rmP0KoymANXJ1wB9Mo5zK6HGOnUkunCkkHFqGuqDgffU+OyxfJJUTQEHXxDw4kdCGbL92C8f4kK7AZDyM8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14395ac7b47aefd0afb9b84b1d09024a6b1ec0535b8239c8eff7fc7788cb9cd4","last_reissued_at":"2026-07-05T05:13:07.000731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:07.000731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Hassan Awadallah, Jianfeng Gao, Jing Gao, Sahaj Agarwal, Subhabrata Mukherjee, XiaoDong Liu, Yaqing Wang","submitted_at":"2022-05-24T23:41:22Z","abstract_excerpt":"Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models. To address this, parameter-efficient fine-tuning (PEFT) techniques were introduced where small trainable components are injected in the PLM and updated during fine-tuning. We propose AdaMix as a general PEFT method that tunes a mixture of adaptation modules -- given the underlying PEFT method of choice -- introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12410","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/2205.12410/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":"2205.12410","created_at":"2026-07-05T05:13:07.000788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12410v2","created_at":"2026-07-05T05:13:07.000788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12410","created_at":"2026-07-05T05:13:07.000788+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQ4VVR5UPLX5","created_at":"2026-07-05T05:13:07.000788+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQ4VVR5UPLX5BL5Z","created_at":"2026-07-05T05:13:07.000788+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQ4VVR5U","created_at":"2026-07-05T05:13:07.000788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11712","citing_title":"Substrate Asymmetry in User-Side Memory: A Diagnostic Framework","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10488","citing_title":"5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05465","citing_title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":249,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":246,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19042","citing_title":"STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ","json":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ.json","graph_json":"https://pith.science/api/pith-number/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/graph.json","events_json":"https://pith.science/api/pith-number/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/events.json","paper":"https://pith.science/paper/CQ4VVR5U"},"agent_actions":{"view_html":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ","download_json":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ.json","view_paper":"https://pith.science/paper/CQ4VVR5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12410&json=true","fetch_graph":"https://pith.science/api/pith-number/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/action/storage_attestation","attest_author":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/action/author_attestation","sign_citation":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/action/citation_signature","submit_replication":"https://pith.science/pith/CQ4VVR5UPLX5BL5ZXBFR2CICJJ/action/replication_record"}},"created_at":"2026-07-05T05:13:07.000788+00:00","updated_at":"2026-07-05T05:13:07.000788+00:00"}