{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QHAQY5GRILLRGHYJEZHNMKQNAJ","short_pith_number":"pith:QHAQY5GR","canonical_record":{"source":{"id":"2505.00582","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T15:14:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5933bd99328452b86d4fb96c1614ab864ab86d995562cdd484db442d2cce87cf","abstract_canon_sha256":"53b73b96bc9f32d77e64c441564a98760fb296264493cd4a9af9d447e15610a1"},"schema_version":"1.0"},"canonical_sha256":"81c10c74d142d7131f09264ed62a0d027cec3bd108cd387dfece20f013f83f39","source":{"kind":"arxiv","id":"2505.00582","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00582","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00582v2","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00582","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_12","alias_value":"QHAQY5GRILLR","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_16","alias_value":"QHAQY5GRILLRGHYJ","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_8","alias_value":"QHAQY5GR","created_at":"2026-07-05T11:37:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QHAQY5GRILLRGHYJEZHNMKQNAJ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.00582","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T15:14:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5933bd99328452b86d4fb96c1614ab864ab86d995562cdd484db442d2cce87cf","abstract_canon_sha256":"53b73b96bc9f32d77e64c441564a98760fb296264493cd4a9af9d447e15610a1"},"schema_version":"1.0"},"canonical_sha256":"81c10c74d142d7131f09264ed62a0d027cec3bd108cd387dfece20f013f83f39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:19.148425Z","signature_b64":"m8lDBZiRyD3RSyXhCF+1VcDnmLn2vszjDOCemCx3tEbjuw9oZddesZfTlTFYTmWtS3x+FWS9sMVYEULoewcMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81c10c74d142d7131f09264ed62a0d027cec3bd108cd387dfece20f013f83f39","last_reissued_at":"2026-07-05T11:37:19.147437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:19.147437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.00582","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":"2026-07-05T11:37:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vu4Jo0tNuwmmSyaDkYk485/GLLgunE+aFhqmjrTZ4DR8u6K0JZNc0bI+/8bJZ7Bn1aeOMMj4LHDP8jJ37KQIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:25:40.579173Z"},"content_sha256":"4911ecf32e60561b99dc5442904d295ba0c9d21b500c6325e5d8e745408efd53","schema_version":"1.0","event_id":"sha256:4911ecf32e60561b99dc5442904d295ba0c9d21b500c6325e5d8e745408efd53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QHAQY5GRILLRGHYJEZHNMKQNAJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Block Circulant Adapter for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Meiqi Wang, Siyu Liao, Xinyu Ding, Zhongfeng Wang","submitted_at":"2025-05-01T15:14:32Z","abstract_excerpt":"Fine-tuning large language models (LLMs) is difficult due to their huge model size. Recent Fourier domain-based methods show potential for reducing fine-tuning costs. We propose a block circulant matrix-based fine-tuning method with a stable training heuristic to leverage the properties of circulant matrices and one-dimensional Fourier transforms to reduce storage and computation costs. Experiments show that our method uses $14\\times$ less number of parameters than VeRA, $16\\times$ smaller than LoRA and $32\\times$ less FLOPs than FourierFT, while maintaining close or better task performance. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00582","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/2505.00582/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":"2026-07-05T11:37:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yJShjAavQaY/1ZFyZ5EWpURiBbDKt/MVdK48hJoE8x8TGEpTEeMvGd6toZ5vntdtz2lJTTqQVKAI+c1gvB5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:25:40.579796Z"},"content_sha256":"645d9594f34be88435df6e8b78c1b021214da41cdd202da202351f1429531755","schema_version":"1.0","event_id":"sha256:645d9594f34be88435df6e8b78c1b021214da41cdd202da202351f1429531755"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHAQY5GRILLRGHYJEZHNMKQNAJ/bundle.json","state_url":"https://pith.science/pith/QHAQY5GRILLRGHYJEZHNMKQNAJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHAQY5GRILLRGHYJEZHNMKQNAJ/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":"2026-08-16T22:25:40Z","links":{"resolver":"https://pith.science/pith/QHAQY5GRILLRGHYJEZHNMKQNAJ","bundle":"https://pith.science/pith/QHAQY5GRILLRGHYJEZHNMKQNAJ/bundle.json","state":"https://pith.science/pith/QHAQY5GRILLRGHYJEZHNMKQNAJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHAQY5GRILLRGHYJEZHNMKQNAJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QHAQY5GRILLRGHYJEZHNMKQNAJ","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":"53b73b96bc9f32d77e64c441564a98760fb296264493cd4a9af9d447e15610a1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T15:14:32Z","title_canon_sha256":"5933bd99328452b86d4fb96c1614ab864ab86d995562cdd484db442d2cce87cf"},"schema_version":"1.0","source":{"id":"2505.00582","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00582","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00582v2","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00582","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_12","alias_value":"QHAQY5GRILLR","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_16","alias_value":"QHAQY5GRILLRGHYJ","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_8","alias_value":"QHAQY5GR","created_at":"2026-07-05T11:37:19Z"}],"graph_snapshots":[{"event_id":"sha256:645d9594f34be88435df6e8b78c1b021214da41cdd202da202351f1429531755","target":"graph","created_at":"2026-07-05T11:37:19Z","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/2505.00582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large language models (LLMs) is difficult due to their huge model size. Recent Fourier domain-based methods show potential for reducing fine-tuning costs. We propose a block circulant matrix-based fine-tuning method with a stable training heuristic to leverage the properties of circulant matrices and one-dimensional Fourier transforms to reduce storage and computation costs. Experiments show that our method uses $14\\times$ less number of parameters than VeRA, $16\\times$ smaller than LoRA and $32\\times$ less FLOPs than FourierFT, while maintaining close or better task performance. O","authors_text":"Meiqi Wang, Siyu Liao, Xinyu Ding, Zhongfeng Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T15:14:32Z","title":"Block Circulant Adapter for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00582","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":"sha256:4911ecf32e60561b99dc5442904d295ba0c9d21b500c6325e5d8e745408efd53","target":"record","created_at":"2026-07-05T11:37:19Z","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":"53b73b96bc9f32d77e64c441564a98760fb296264493cd4a9af9d447e15610a1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T15:14:32Z","title_canon_sha256":"5933bd99328452b86d4fb96c1614ab864ab86d995562cdd484db442d2cce87cf"},"schema_version":"1.0","source":{"id":"2505.00582","kind":"arxiv","version":2}},"canonical_sha256":"81c10c74d142d7131f09264ed62a0d027cec3bd108cd387dfece20f013f83f39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81c10c74d142d7131f09264ed62a0d027cec3bd108cd387dfece20f013f83f39","first_computed_at":"2026-07-05T11:37:19.147437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:19.147437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m8lDBZiRyD3RSyXhCF+1VcDnmLn2vszjDOCemCx3tEbjuw9oZddesZfTlTFYTmWtS3x+FWS9sMVYEULoewcMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:19.148425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00582","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4911ecf32e60561b99dc5442904d295ba0c9d21b500c6325e5d8e745408efd53","sha256:645d9594f34be88435df6e8b78c1b021214da41cdd202da202351f1429531755"],"state_sha256":"f8ab2f147accf411b2381562c2c6c3074f3e9595588b53364662dec93bde853a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eF+wh4lTlx163mmkwtKegGn9XQiOVHHprU6Fp+HU0E4VpaMk7OjxM1PKn07I28w6+bN7s/QGzeyXFRmv+mIRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:25:40.583476Z","bundle_sha256":"5e946136a52b5e2765066bc44a5d9691423f531ba5b85e262f5ee76561033cdc"}}