{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:27PUZSXTRKO73WPSH4V5BDA3P5","short_pith_number":"pith:27PUZSXT","canonical_record":{"source":{"id":"2405.19597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T01:27:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"abcb9b20c64106734625141adc003da8e259d13180dd8f5bd63e4f32ba228f6a","abstract_canon_sha256":"3887ac91ea9d9e6d0265e40371c0094e1d74d864befca00892253b6bf0e38963"},"schema_version":"1.0"},"canonical_sha256":"d7df4ccaf38a9dfdd9f23f2bd08c1b7f4ceed61d6eafeea8095b4372930d576f","source":{"kind":"arxiv","id":"2405.19597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19597","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19597v1","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19597","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"27PUZSXTRKO7","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"27PUZSXTRKO73WPS","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"27PUZSXT","created_at":"2026-07-05T08:25:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:27PUZSXTRKO73WPSH4V5BDA3P5","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T01:27:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"abcb9b20c64106734625141adc003da8e259d13180dd8f5bd63e4f32ba228f6a","abstract_canon_sha256":"3887ac91ea9d9e6d0265e40371c0094e1d74d864befca00892253b6bf0e38963"},"schema_version":"1.0"},"canonical_sha256":"d7df4ccaf38a9dfdd9f23f2bd08c1b7f4ceed61d6eafeea8095b4372930d576f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:09.991709Z","signature_b64":"0R6LtdEyB34PB0vsoBjgR+4v4jFsVJ0n715RShWoIz5tWKbhza1qbbaMJP0RTtesTTloCehBeRN5/pR2EPXsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7df4ccaf38a9dfdd9f23f2bd08c1b7f4ceed61d6eafeea8095b4372930d576f","last_reissued_at":"2026-07-05T08:25:09.991151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:09.991151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19597","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":"2026-07-05T08:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v0S+QGco6ZmQXDcIQx08GHi1fFweueSPhPE6PugD/Yr6ZbwNnlsIoHkgNaeE537EO+bDfl4j/JnPtesH/IeWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:00:41.582181Z"},"content_sha256":"31d37936dd36fdb93658e1290534cd58f17ddb7255d6fbfdeb9529de07bc9c45","schema_version":"1.0","event_id":"sha256:31d37936dd36fdb93658e1290534cd58f17ddb7255d6fbfdeb9529de07bc9c45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:27PUZSXTRKO73WPSH4V5BDA3P5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aditya Vavre, Aleksandar Bojchevski, Alex Dimakis, Aneesh Shetty, Atula Tejaswi, Eunsol Choi, Gautham Krishna Gudur, Joydeep Ghosh, Sujay Sanghavi, Vijay Lingam","submitted_at":"2024-05-30T01:27:43Z","abstract_excerpt":"Popular parameter-efficient fine-tuning (PEFT) methods, such as LoRA and its variants, freeze pre-trained model weights \\(W\\) and inject learnable matrices \\(\\Delta W\\). These \\(\\Delta W\\) matrices are structured for efficient parameterization, often using techniques like low-rank approximations or scaling vectors. However, these methods typically show a performance gap compared to full fine-tuning. Although recent PEFT methods have narrowed this gap, they do so at the cost of additional learnable parameters. We propose SVFT, a simple approach that fundamentally differs from existing methods: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19597","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/2405.19597/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":"2026-07-05T08:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lGb5gZ7JZemKgKNDJ5/ExEyBuqPTz8DB4Q7Sj7w7OKmYwYZVkW4FM/jSzzC2da27Vkdt0JVxvHn2Ucy1ZpBeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:00:41.583066Z"},"content_sha256":"19a2ec3acab378db0f3b3543ad5369082582198cde5f2473fe3a1329b8d63886","schema_version":"1.0","event_id":"sha256:19a2ec3acab378db0f3b3543ad5369082582198cde5f2473fe3a1329b8d63886"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/27PUZSXTRKO73WPSH4V5BDA3P5/bundle.json","state_url":"https://pith.science/pith/27PUZSXTRKO73WPSH4V5BDA3P5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/27PUZSXTRKO73WPSH4V5BDA3P5/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":"2026-08-09T21:00:41Z","links":{"resolver":"https://pith.science/pith/27PUZSXTRKO73WPSH4V5BDA3P5","bundle":"https://pith.science/pith/27PUZSXTRKO73WPSH4V5BDA3P5/bundle.json","state":"https://pith.science/pith/27PUZSXTRKO73WPSH4V5BDA3P5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/27PUZSXTRKO73WPSH4V5BDA3P5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:27PUZSXTRKO73WPSH4V5BDA3P5","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":"3887ac91ea9d9e6d0265e40371c0094e1d74d864befca00892253b6bf0e38963","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T01:27:43Z","title_canon_sha256":"abcb9b20c64106734625141adc003da8e259d13180dd8f5bd63e4f32ba228f6a"},"schema_version":"1.0","source":{"id":"2405.19597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19597","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19597v1","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19597","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"27PUZSXTRKO7","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"27PUZSXTRKO73WPS","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"27PUZSXT","created_at":"2026-07-05T08:25:09Z"}],"graph_snapshots":[{"event_id":"sha256:19a2ec3acab378db0f3b3543ad5369082582198cde5f2473fe3a1329b8d63886","target":"graph","created_at":"2026-07-05T08:25:09Z","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/2405.19597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Popular parameter-efficient fine-tuning (PEFT) methods, such as LoRA and its variants, freeze pre-trained model weights \\(W\\) and inject learnable matrices \\(\\Delta W\\). These \\(\\Delta W\\) matrices are structured for efficient parameterization, often using techniques like low-rank approximations or scaling vectors. However, these methods typically show a performance gap compared to full fine-tuning. Although recent PEFT methods have narrowed this gap, they do so at the cost of additional learnable parameters. We propose SVFT, a simple approach that fundamentally differs from existing methods: ","authors_text":"Aditya Vavre, Aleksandar Bojchevski, Alex Dimakis, Aneesh Shetty, Atula Tejaswi, Eunsol Choi, Gautham Krishna Gudur, Joydeep Ghosh, Sujay Sanghavi, Vijay Lingam","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T01:27:43Z","title":"SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19597","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":"sha256:31d37936dd36fdb93658e1290534cd58f17ddb7255d6fbfdeb9529de07bc9c45","target":"record","created_at":"2026-07-05T08:25:09Z","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":"3887ac91ea9d9e6d0265e40371c0094e1d74d864befca00892253b6bf0e38963","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T01:27:43Z","title_canon_sha256":"abcb9b20c64106734625141adc003da8e259d13180dd8f5bd63e4f32ba228f6a"},"schema_version":"1.0","source":{"id":"2405.19597","kind":"arxiv","version":1}},"canonical_sha256":"d7df4ccaf38a9dfdd9f23f2bd08c1b7f4ceed61d6eafeea8095b4372930d576f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7df4ccaf38a9dfdd9f23f2bd08c1b7f4ceed61d6eafeea8095b4372930d576f","first_computed_at":"2026-07-05T08:25:09.991151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:09.991151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0R6LtdEyB34PB0vsoBjgR+4v4jFsVJ0n715RShWoIz5tWKbhza1qbbaMJP0RTtesTTloCehBeRN5/pR2EPXsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:09.991709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31d37936dd36fdb93658e1290534cd58f17ddb7255d6fbfdeb9529de07bc9c45","sha256:19a2ec3acab378db0f3b3543ad5369082582198cde5f2473fe3a1329b8d63886"],"state_sha256":"6cf0986ba3675242bf36ce9eb6a5be0477602cd0b266148efa14d237c2412b8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vgmyz4yuVUrxeNHIXPP5wydIia4srXtmFAkXQBbWySa9LGEx3qU8rjRVr8qtIpza5HnIfq7UOow+a5dMJfu4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:00:41.590288Z","bundle_sha256":"75a558017dc8ab303ed02d952618ddbab543e2ef8a0e00c701cd764c5016368e"}}