{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SWOJYZRKLED645KZMQBIFZKWCH","short_pith_number":"pith:SWOJYZRK","canonical_record":{"source":{"id":"2508.21810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T17:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"ff6f6b678dd338ffbe89bc64bdabb70c62604856720655ef8a8f63b1564e08dc","abstract_canon_sha256":"8fc5d213e4f3480b866602abe3c1cd4109f061ce46ab2f8c107e8475930d97b4"},"schema_version":"1.0"},"canonical_sha256":"959c9c662a5907ee7559640282e55611d77f7007fce2c48a6cdcff6d3f51a90e","source":{"kind":"arxiv","id":"2508.21810","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21810","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21810v1","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21810","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"SWOJYZRKLED6","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"SWOJYZRKLED645KZ","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"SWOJYZRK","created_at":"2026-07-05T12:01:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SWOJYZRKLED645KZMQBIFZKWCH","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T17:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"ff6f6b678dd338ffbe89bc64bdabb70c62604856720655ef8a8f63b1564e08dc","abstract_canon_sha256":"8fc5d213e4f3480b866602abe3c1cd4109f061ce46ab2f8c107e8475930d97b4"},"schema_version":"1.0"},"canonical_sha256":"959c9c662a5907ee7559640282e55611d77f7007fce2c48a6cdcff6d3f51a90e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:50.026194Z","signature_b64":"dRudq13iykoF9/KD8/9GSfebP1LbWpGgKK8jpMHsW/BEMRiMtHyfq/S7ReUfNdc3z0sp5b+ujfGKPMI3BvWjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"959c9c662a5907ee7559640282e55611d77f7007fce2c48a6cdcff6d3f51a90e","last_reissued_at":"2026-07-05T12:01:50.025696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:50.025696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21810","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z18YT0IRMC7/BL6HZhyALvqfASmnw6dF5NMcvsBkA01+ch+2HlTfFBp7SIZmRfk2tngDPd6woqnw+pRDNr37AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:51:24.612505Z"},"content_sha256":"a8243c28791d3b4ac4489906c47d18b27b0313bf9c90d8500c523570a2bbbf7e","schema_version":"1.0","event_id":"sha256:a8243c28791d3b4ac4489906c47d18b27b0313bf9c90d8500c523570a2bbbf7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SWOJYZRKLED645KZMQBIFZKWCH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anirudh Bharadwaj, Jessica Liang","submitted_at":"2025-08-29T17:47:27Z","abstract_excerpt":"The growing scale of Large Language Models (LLMs) has necessitated the development of parameter-efficient fine-tuning techniques. Low-Rank Adaptation (LoRA) has emerged as a promising approach, reducing the number of trainable parameters by applying low-rank updates to pretrained weights. While standard LoRA learns both update factors directly, several recent variants first initialize those matrices via an SVD of the pretrained weights -- an operation that can be expensive on large models and yields singular vectors that are not always easy to interpret. In this work, we extract an orthonormal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21810","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/2508.21810/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5wi7cnG8kkgrRJEfDbbfiM50Jpig1Xlr3zOOmDGYpfvrHGGKw/jR0DGTaEL/tFJOyrlYblYH3aMJbVV2R8vADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:51:24.613184Z"},"content_sha256":"41a303e8f9c7599d3c7d0eb18bf4fdbef81832d39105a4ccfc3ddb1bc669aadd","schema_version":"1.0","event_id":"sha256:41a303e8f9c7599d3c7d0eb18bf4fdbef81832d39105a4ccfc3ddb1bc669aadd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWOJYZRKLED645KZMQBIFZKWCH/bundle.json","state_url":"https://pith.science/pith/SWOJYZRKLED645KZMQBIFZKWCH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWOJYZRKLED645KZMQBIFZKWCH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T01:51:24Z","links":{"resolver":"https://pith.science/pith/SWOJYZRKLED645KZMQBIFZKWCH","bundle":"https://pith.science/pith/SWOJYZRKLED645KZMQBIFZKWCH/bundle.json","state":"https://pith.science/pith/SWOJYZRKLED645KZMQBIFZKWCH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWOJYZRKLED645KZMQBIFZKWCH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SWOJYZRKLED645KZMQBIFZKWCH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8fc5d213e4f3480b866602abe3c1cd4109f061ce46ab2f8c107e8475930d97b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T17:47:27Z","title_canon_sha256":"ff6f6b678dd338ffbe89bc64bdabb70c62604856720655ef8a8f63b1564e08dc"},"schema_version":"1.0","source":{"id":"2508.21810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21810","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21810v1","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21810","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"SWOJYZRKLED6","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"SWOJYZRKLED645KZ","created_at":"2026-07-05T12:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"SWOJYZRK","created_at":"2026-07-05T12:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:41a303e8f9c7599d3c7d0eb18bf4fdbef81832d39105a4ccfc3ddb1bc669aadd","target":"graph","created_at":"2026-07-05T12:01:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.21810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing scale of Large Language Models (LLMs) has necessitated the development of parameter-efficient fine-tuning techniques. Low-Rank Adaptation (LoRA) has emerged as a promising approach, reducing the number of trainable parameters by applying low-rank updates to pretrained weights. While standard LoRA learns both update factors directly, several recent variants first initialize those matrices via an SVD of the pretrained weights -- an operation that can be expensive on large models and yields singular vectors that are not always easy to interpret. In this work, we extract an orthonormal","authors_text":"Anirudh Bharadwaj, Jessica Liang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T17:47:27Z","title":"QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21810","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a8243c28791d3b4ac4489906c47d18b27b0313bf9c90d8500c523570a2bbbf7e","target":"record","created_at":"2026-07-05T12:01:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8fc5d213e4f3480b866602abe3c1cd4109f061ce46ab2f8c107e8475930d97b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T17:47:27Z","title_canon_sha256":"ff6f6b678dd338ffbe89bc64bdabb70c62604856720655ef8a8f63b1564e08dc"},"schema_version":"1.0","source":{"id":"2508.21810","kind":"arxiv","version":1}},"canonical_sha256":"959c9c662a5907ee7559640282e55611d77f7007fce2c48a6cdcff6d3f51a90e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"959c9c662a5907ee7559640282e55611d77f7007fce2c48a6cdcff6d3f51a90e","first_computed_at":"2026-07-05T12:01:50.025696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:50.025696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dRudq13iykoF9/KD8/9GSfebP1LbWpGgKK8jpMHsW/BEMRiMtHyfq/S7ReUfNdc3z0sp5b+ujfGKPMI3BvWjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:50.026194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8243c28791d3b4ac4489906c47d18b27b0313bf9c90d8500c523570a2bbbf7e","sha256:41a303e8f9c7599d3c7d0eb18bf4fdbef81832d39105a4ccfc3ddb1bc669aadd"],"state_sha256":"7fbe41ab4a2cb64e93852d91c98782d1e91e4fce0255537c6a176ca088dfa6d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xva38o7LPr6dZIC/TjSQnikjAJkXiozGHmsti7KOjIYvW88H/bIAqivNqvQnq4r/Fe+rBFsg7dMez8TvAY/ECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:51:24.618562Z","bundle_sha256":"23e8c6b3f81b913edcbcd48f1ccd36ed6930b5cf224197912eb42ec33a2b9766"}}