{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UGKPSNQWEAYJTMST64FM2EZCA4","short_pith_number":"pith:UGKPSNQW","canonical_record":{"source":{"id":"2412.09250","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T13:04:54Z","cross_cats_sorted":["math.GT","stat.ML"],"title_canon_sha256":"5e7cd535b02c3d6818e491f3e3e39ff0b60741b7d2c017550743e5ba7f933936","abstract_canon_sha256":"fbd18714092d79000a4d47af2048590b3ce86292841947c102a40b8051ab6718"},"schema_version":"1.0"},"canonical_sha256":"a194f93616203099b253f70acd13220738ba2490e1d6ab2704a42a79273d5c94","source":{"kind":"arxiv","id":"2412.09250","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09250","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09250v3","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09250","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_12","alias_value":"UGKPSNQWEAYJ","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_16","alias_value":"UGKPSNQWEAYJTMST","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_8","alias_value":"UGKPSNQW","created_at":"2026-07-05T09:50:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UGKPSNQWEAYJTMST64FM2EZCA4","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09250","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T13:04:54Z","cross_cats_sorted":["math.GT","stat.ML"],"title_canon_sha256":"5e7cd535b02c3d6818e491f3e3e39ff0b60741b7d2c017550743e5ba7f933936","abstract_canon_sha256":"fbd18714092d79000a4d47af2048590b3ce86292841947c102a40b8051ab6718"},"schema_version":"1.0"},"canonical_sha256":"a194f93616203099b253f70acd13220738ba2490e1d6ab2704a42a79273d5c94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:55.498205Z","signature_b64":"TKE4tvvCJDq+fRcInv5kwZQidTO+fK39GE5BVtiQrtAuN4Afm5eO3Exo/ebhZ4nltUcfqfAIp402WES4jLkXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a194f93616203099b253f70acd13220738ba2490e1d6ab2704a42a79273d5c94","last_reissued_at":"2026-07-05T09:50:55.497725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:55.497725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09250","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sCH98AvngN5eONVS2fPhcgJrxFqJey9LcTmjMlheqe3q6FEdD30/d9eBRB2vYyPWyKk4fQ4livzixra6FdHCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:20:39.325501Z"},"content_sha256":"b1af0d23207b2d9cd3821eecd8edd6be60bc2fa6b7f892982d0f70d789ce0774","schema_version":"1.0","event_id":"sha256:b1af0d23207b2d9cd3821eecd8edd6be60bc2fa6b7f892982d0f70d789ce0774"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UGKPSNQWEAYJTMST64FM2EZCA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdessalam Ed-dib, Amine Mohamed Aboussalah, Zhanibek Datbayev","submitted_at":"2024-12-12T13:04:54Z","abstract_excerpt":"Fine-tuning large language models (LLMs) is computationally intensive because it requires updating all parameters. Low-Rank Adaptation (LoRA) improves efficiency by modifying only a subset of weights but introduces a trade-off between expressivity and computational cost: lower ranks reduce resources but limit expressiveness, while higher ranks enhance expressivity at increased cost. Despite recent advances in adaptive LoRA techniques, existing methods fail to provide a theoretical basis for optimizing the trade-off between model performance and efficiency. We propose Geometric Low-Rank Adaptat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09250","kind":"arxiv","version":3},"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/2412.09250/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":"2026-07-05T09:50:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kN6x3o7UQy0TRHY6FO0VhvrqEyDBQm8u/TQQEpj9oxqY0+9qo+PeltyB75d3uOuBc8oSboobfTArFrjD93MRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:20:39.326074Z"},"content_sha256":"268acabb5400d4349860b79a5bd1294ef037f7f3acf326c810342da93bac2e00","schema_version":"1.0","event_id":"sha256:268acabb5400d4349860b79a5bd1294ef037f7f3acf326c810342da93bac2e00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UGKPSNQWEAYJTMST64FM2EZCA4/bundle.json","state_url":"https://pith.science/pith/UGKPSNQWEAYJTMST64FM2EZCA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UGKPSNQWEAYJTMST64FM2EZCA4/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":"2026-08-09T20:20:39Z","links":{"resolver":"https://pith.science/pith/UGKPSNQWEAYJTMST64FM2EZCA4","bundle":"https://pith.science/pith/UGKPSNQWEAYJTMST64FM2EZCA4/bundle.json","state":"https://pith.science/pith/UGKPSNQWEAYJTMST64FM2EZCA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UGKPSNQWEAYJTMST64FM2EZCA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UGKPSNQWEAYJTMST64FM2EZCA4","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":"fbd18714092d79000a4d47af2048590b3ce86292841947c102a40b8051ab6718","cross_cats_sorted":["math.GT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T13:04:54Z","title_canon_sha256":"5e7cd535b02c3d6818e491f3e3e39ff0b60741b7d2c017550743e5ba7f933936"},"schema_version":"1.0","source":{"id":"2412.09250","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09250","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09250v3","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09250","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_12","alias_value":"UGKPSNQWEAYJ","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_16","alias_value":"UGKPSNQWEAYJTMST","created_at":"2026-07-05T09:50:55Z"},{"alias_kind":"pith_short_8","alias_value":"UGKPSNQW","created_at":"2026-07-05T09:50:55Z"}],"graph_snapshots":[{"event_id":"sha256:268acabb5400d4349860b79a5bd1294ef037f7f3acf326c810342da93bac2e00","target":"graph","created_at":"2026-07-05T09:50:55Z","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/2412.09250/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 computationally intensive because it requires updating all parameters. Low-Rank Adaptation (LoRA) improves efficiency by modifying only a subset of weights but introduces a trade-off between expressivity and computational cost: lower ranks reduce resources but limit expressiveness, while higher ranks enhance expressivity at increased cost. Despite recent advances in adaptive LoRA techniques, existing methods fail to provide a theoretical basis for optimizing the trade-off between model performance and efficiency. We propose Geometric Low-Rank Adaptat","authors_text":"Abdessalam Ed-dib, Amine Mohamed Aboussalah, Zhanibek Datbayev","cross_cats":["math.GT","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T13:04:54Z","title":"GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09250","kind":"arxiv","version":3},"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:b1af0d23207b2d9cd3821eecd8edd6be60bc2fa6b7f892982d0f70d789ce0774","target":"record","created_at":"2026-07-05T09:50:55Z","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":"fbd18714092d79000a4d47af2048590b3ce86292841947c102a40b8051ab6718","cross_cats_sorted":["math.GT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T13:04:54Z","title_canon_sha256":"5e7cd535b02c3d6818e491f3e3e39ff0b60741b7d2c017550743e5ba7f933936"},"schema_version":"1.0","source":{"id":"2412.09250","kind":"arxiv","version":3}},"canonical_sha256":"a194f93616203099b253f70acd13220738ba2490e1d6ab2704a42a79273d5c94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a194f93616203099b253f70acd13220738ba2490e1d6ab2704a42a79273d5c94","first_computed_at":"2026-07-05T09:50:55.497725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:55.497725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TKE4tvvCJDq+fRcInv5kwZQidTO+fK39GE5BVtiQrtAuN4Afm5eO3Exo/ebhZ4nltUcfqfAIp402WES4jLkXDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:55.498205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09250","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1af0d23207b2d9cd3821eecd8edd6be60bc2fa6b7f892982d0f70d789ce0774","sha256:268acabb5400d4349860b79a5bd1294ef037f7f3acf326c810342da93bac2e00"],"state_sha256":"1631ee8b0b19eea592fefb4f80a436c80e4585cd85c63465d00882f7d6524866"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdW6tNg6gYI28iPGTez9GU+h6kd6nqDm/vuKKKuSN+yqgFMNkvBVnfrwl2XxO9hMKCnPOqZ6KHovhFmUwZM0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:20:39.332208Z","bundle_sha256":"3c42ad3871f18c30a566c5bba06e3f2f1cae6f22d14c2793002b9c54cda4dec6"}}