{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M73G7TVKY4364CEZXLCYMPP5B3","short_pith_number":"pith:M73G7TVK","schema_version":"1.0","canonical_sha256":"67f66fceaac737ee0899bac5863dfd0ed7ea827c6e928048a91236d2ef1adac4","source":{"kind":"arxiv","id":"2506.07621","version":1},"attestation_state":"computed","paper":{"title":"LoRMA: Low-Rank Multiplicative Adaptation for LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashutosh Modi, Harsh Bihany, Shubham Patel","submitted_at":"2025-06-09T10:36:46Z","abstract_excerpt":"Large Language Models have shown remarkable capabilities in the NLP domain. Their effectiveness can mainly be attributed to their ability to adapt to an array of downstream tasks. However, generally, full fine-tuning is a computationally expensive job. To mitigate this, many techniques have been developed that prime efficiency, a prominent one being Low-Rank Adaptation (LoRA). However, LoRA and its variants employ re-parametrized additive updates. In this paper, we propose Low-Rank Multiplicative Adaptation (LoRMA), which shifts the paradigm of additive updates to a richer space of matrix mult"},"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":"2506.07621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T10:36:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"314dec351d5b3299837af2adde76a093ebb4069948579a1c67027de0ddd7855d","abstract_canon_sha256":"fd3ec5954136c4c135665e0cc184840317f1c9366c15767072ba95f2678b528c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:30.460566Z","signature_b64":"lphm3EVSUPwmFlD5rKK6Z8VF6YnrIbJTpcJeY9gjyfh4lMeLX6qnTWm7kK4LtKbHjHy6m5e59Fe65Eu75WGpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f66fceaac737ee0899bac5863dfd0ed7ea827c6e928048a91236d2ef1adac4","last_reissued_at":"2026-07-05T11:18:30.460041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:30.460041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoRMA: Low-Rank Multiplicative Adaptation for LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashutosh Modi, Harsh Bihany, Shubham Patel","submitted_at":"2025-06-09T10:36:46Z","abstract_excerpt":"Large Language Models have shown remarkable capabilities in the NLP domain. Their effectiveness can mainly be attributed to their ability to adapt to an array of downstream tasks. However, generally, full fine-tuning is a computationally expensive job. To mitigate this, many techniques have been developed that prime efficiency, a prominent one being Low-Rank Adaptation (LoRA). However, LoRA and its variants employ re-parametrized additive updates. In this paper, we propose Low-Rank Multiplicative Adaptation (LoRMA), which shifts the paradigm of additive updates to a richer space of matrix mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07621","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/2506.07621/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":"2506.07621","created_at":"2026-07-05T11:18:30.460093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07621v1","created_at":"2026-07-05T11:18:30.460093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07621","created_at":"2026-07-05T11:18:30.460093+00:00"},{"alias_kind":"pith_short_12","alias_value":"M73G7TVKY436","created_at":"2026-07-05T11:18:30.460093+00:00"},{"alias_kind":"pith_short_16","alias_value":"M73G7TVKY4364CEZ","created_at":"2026-07-05T11:18:30.460093+00:00"},{"alias_kind":"pith_short_8","alias_value":"M73G7TVK","created_at":"2026-07-05T11:18:30.460093+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/M73G7TVKY4364CEZXLCYMPP5B3","json":"https://pith.science/pith/M73G7TVKY4364CEZXLCYMPP5B3.json","graph_json":"https://pith.science/api/pith-number/M73G7TVKY4364CEZXLCYMPP5B3/graph.json","events_json":"https://pith.science/api/pith-number/M73G7TVKY4364CEZXLCYMPP5B3/events.json","paper":"https://pith.science/paper/M73G7TVK"},"agent_actions":{"view_html":"https://pith.science/pith/M73G7TVKY4364CEZXLCYMPP5B3","download_json":"https://pith.science/pith/M73G7TVKY4364CEZXLCYMPP5B3.json","view_paper":"https://pith.science/paper/M73G7TVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07621&json=true","fetch_graph":"https://pith.science/api/pith-number/M73G7TVKY4364CEZXLCYMPP5B3/graph.json","fetch_events":"https://pith.science/api/pith-number/M73G7TVKY4364CEZXLCYMPP5B3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M73G7TVKY4364CEZXLCYMPP5B3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M73G7TVKY4364CEZXLCYMPP5B3/action/storage_attestation","attest_author":"https://pith.science/pith/M73G7TVKY4364CEZXLCYMPP5B3/action/author_attestation","sign_citation":"https://pith.science/pith/M73G7TVKY4364CEZXLCYMPP5B3/action/citation_signature","submit_replication":"https://pith.science/pith/M73G7TVKY4364CEZXLCYMPP5B3/action/replication_record"}},"created_at":"2026-07-05T11:18:30.460093+00:00","updated_at":"2026-07-05T11:18:30.460093+00:00"}