{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AC6QXDGZIAPLO3LLPN75DCVQYQ","short_pith_number":"pith:AC6QXDGZ","canonical_record":{"source":{"id":"2210.07558","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T06:29:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bbf8ceac32983efc8a78d9aee4d5adb3446b546f60e0d8ed60981b03143cb887","abstract_canon_sha256":"f94feecabd754d7efad182f5622f4303ef4e27d05b61b238247221a813b6b04f"},"schema_version":"1.0"},"canonical_sha256":"00bd0b8cd9401eb76d6b7b7fd18ab0c41367bcdd94121c430d1741d3e2d18e18","source":{"kind":"arxiv","id":"2210.07558","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07558","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07558v2","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07558","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"AC6QXDGZIAPL","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"AC6QXDGZIAPLO3LL","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"AC6QXDGZ","created_at":"2026-07-05T06:02:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AC6QXDGZIAPLO3LLPN75DCVQYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2210.07558","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T06:29:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bbf8ceac32983efc8a78d9aee4d5adb3446b546f60e0d8ed60981b03143cb887","abstract_canon_sha256":"f94feecabd754d7efad182f5622f4303ef4e27d05b61b238247221a813b6b04f"},"schema_version":"1.0"},"canonical_sha256":"00bd0b8cd9401eb76d6b7b7fd18ab0c41367bcdd94121c430d1741d3e2d18e18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:30.173235Z","signature_b64":"KbHMx49JLbUvs3hVuG++D3VzHPVwhVdTp0DRe2qKS6WZ+/GAWth3QZQg1Y12ff/M6O733zjXhE/VHy5HziuwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00bd0b8cd9401eb76d6b7b7fd18ab0c41367bcdd94121c430d1741d3e2d18e18","last_reissued_at":"2026-07-05T06:02:30.172751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:30.172751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.07558","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wAYMZxfP9SgTDqyqCr9KBUdaYinW53vAXu+6xXgjTekcxWGSGGFcqwSppzL/z3trgSHTfv3NG5fFKmBoR+qsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:08:14.109808Z"},"content_sha256":"b80a35a7504d5fefcc157b3220bc214a0edc4cc8cedec7491e7dc4a832185c5b","schema_version":"1.0","event_id":"sha256:b80a35a7504d5fefcc157b3220bc214a0edc4cc8cedec7491e7dc4a832185c5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AC6QXDGZIAPLO3LLPN75DCVQYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Ghodsi, Ivan Kobyzev, Mehdi Rezagholizadeh, Mojtaba Valipour","submitted_at":"2022-10-14T06:29:22Z","abstract_excerpt":"With the ever-growing size of pretrained models (PMs), fine-tuning them has become more expensive and resource-hungry. As a remedy, low-rank adapters (LoRA) keep the main pretrained weights of the model frozen and just introduce some learnable truncated SVD modules (so-called LoRA blocks) to the model. While LoRA blocks are parameter-efficient, they suffer from two major problems: first, the size of these blocks is fixed and cannot be modified after training (for example, if we need to change the rank of LoRA blocks, then we need to re-train them from scratch); second, optimizing their rank re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07558","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/2210.07558/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":"2026-07-05T06:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2kP2eA5taWTnYwbmyVJqte+8vXdF51JfYnRimKcU/K0mRkKyPfS9ONlWVZTLTkwwEVVdBDEAHP0mYjHLxaKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:08:14.110325Z"},"content_sha256":"7a1ef327caf20df38dbc9a6676e74e82f896ce9ee6a82f47245c22fb5a3964a6","schema_version":"1.0","event_id":"sha256:7a1ef327caf20df38dbc9a6676e74e82f896ce9ee6a82f47245c22fb5a3964a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AC6QXDGZIAPLO3LLPN75DCVQYQ/bundle.json","state_url":"https://pith.science/pith/AC6QXDGZIAPLO3LLPN75DCVQYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AC6QXDGZIAPLO3LLPN75DCVQYQ/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":"2026-08-07T14:08:14Z","links":{"resolver":"https://pith.science/pith/AC6QXDGZIAPLO3LLPN75DCVQYQ","bundle":"https://pith.science/pith/AC6QXDGZIAPLO3LLPN75DCVQYQ/bundle.json","state":"https://pith.science/pith/AC6QXDGZIAPLO3LLPN75DCVQYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AC6QXDGZIAPLO3LLPN75DCVQYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AC6QXDGZIAPLO3LLPN75DCVQYQ","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":"f94feecabd754d7efad182f5622f4303ef4e27d05b61b238247221a813b6b04f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T06:29:22Z","title_canon_sha256":"bbf8ceac32983efc8a78d9aee4d5adb3446b546f60e0d8ed60981b03143cb887"},"schema_version":"1.0","source":{"id":"2210.07558","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07558","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07558v2","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07558","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"AC6QXDGZIAPL","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"AC6QXDGZIAPLO3LL","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"AC6QXDGZ","created_at":"2026-07-05T06:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:7a1ef327caf20df38dbc9a6676e74e82f896ce9ee6a82f47245c22fb5a3964a6","target":"graph","created_at":"2026-07-05T06:02:30Z","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/2210.07558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the ever-growing size of pretrained models (PMs), fine-tuning them has become more expensive and resource-hungry. As a remedy, low-rank adapters (LoRA) keep the main pretrained weights of the model frozen and just introduce some learnable truncated SVD modules (so-called LoRA blocks) to the model. While LoRA blocks are parameter-efficient, they suffer from two major problems: first, the size of these blocks is fixed and cannot be modified after training (for example, if we need to change the rank of LoRA blocks, then we need to re-train them from scratch); second, optimizing their rank re","authors_text":"Ali Ghodsi, Ivan Kobyzev, Mehdi Rezagholizadeh, Mojtaba Valipour","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T06:29:22Z","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07558","kind":"arxiv","version":2},"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:b80a35a7504d5fefcc157b3220bc214a0edc4cc8cedec7491e7dc4a832185c5b","target":"record","created_at":"2026-07-05T06:02:30Z","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":"f94feecabd754d7efad182f5622f4303ef4e27d05b61b238247221a813b6b04f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T06:29:22Z","title_canon_sha256":"bbf8ceac32983efc8a78d9aee4d5adb3446b546f60e0d8ed60981b03143cb887"},"schema_version":"1.0","source":{"id":"2210.07558","kind":"arxiv","version":2}},"canonical_sha256":"00bd0b8cd9401eb76d6b7b7fd18ab0c41367bcdd94121c430d1741d3e2d18e18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00bd0b8cd9401eb76d6b7b7fd18ab0c41367bcdd94121c430d1741d3e2d18e18","first_computed_at":"2026-07-05T06:02:30.172751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:30.172751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KbHMx49JLbUvs3hVuG++D3VzHPVwhVdTp0DRe2qKS6WZ+/GAWth3QZQg1Y12ff/M6O733zjXhE/VHy5HziuwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:30.173235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07558","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b80a35a7504d5fefcc157b3220bc214a0edc4cc8cedec7491e7dc4a832185c5b","sha256:7a1ef327caf20df38dbc9a6676e74e82f896ce9ee6a82f47245c22fb5a3964a6"],"state_sha256":"f6a84929dcd13cb64b530be57a9d48e02b160e34ccc5379fac37c2ed06969cb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCPz1jjHFGtFZDaTf9Dd0iE5rN/MnBQT6x/fxq9jC+tOW9useQl1VELs93tmyZjALmw0b4B9dzG/mWKx+CUeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T14:08:14.123145Z","bundle_sha256":"4ee77fda1c84f2167b5dedc945d4f7ceae6a4ea5a8b761a7d9d9bf3b571a03f5"}}