{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SZRT3K3MIOHIDPNA5STEVVL4FL","short_pith_number":"pith:SZRT3K3M","canonical_record":{"source":{"id":"2505.24174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T03:34:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2161330610b997e9c9661f6da14b0cb97595dbe763d1a23946c30d330a967d09","abstract_canon_sha256":"c406034d3654a10fdccbc1b97c4b931ea674c32cab10cd7aad965542380f6341"},"schema_version":"1.0"},"canonical_sha256":"96633dab6c438e81bda0eca64ad57c2ae8562c50e72f6a4e7ab3ec44a9613684","source":{"kind":"arxiv","id":"2505.24174","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24174","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24174v1","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24174","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"SZRT3K3MIOHI","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_16","alias_value":"SZRT3K3MIOHIDPNA","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_8","alias_value":"SZRT3K3M","created_at":"2026-07-05T11:12:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SZRT3K3MIOHIDPNA5STEVVL4FL","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T03:34:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2161330610b997e9c9661f6da14b0cb97595dbe763d1a23946c30d330a967d09","abstract_canon_sha256":"c406034d3654a10fdccbc1b97c4b931ea674c32cab10cd7aad965542380f6341"},"schema_version":"1.0"},"canonical_sha256":"96633dab6c438e81bda0eca64ad57c2ae8562c50e72f6a4e7ab3ec44a9613684","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:43.392740Z","signature_b64":"2a2aUZOpe0g1eHRfYNJzXE9ZWfVvhDrxbn6owEO7+VqzRMZkbzZPWcyyLn/3y7au5fPlYPlFV5fZAQ/o43DSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96633dab6c438e81bda0eca64ad57c2ae8562c50e72f6a4e7ab3ec44a9613684","last_reissued_at":"2026-07-05T11:12:43.392172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:43.392172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24174","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":"2026-07-05T11:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bKY+0qrZFnxCBYSbg/J2jfs70VipwP/wB6ocGN3K/fuptH2jQB9tM35DzmGFZl+l09jJXkKFLTU3IcYx1fBkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:42:59.458459Z"},"content_sha256":"d50cee73de895fc272a6cd163323f19b348f183b3d721b3688b2f90034185392","schema_version":"1.0","event_id":"sha256:d50cee73de895fc272a6cd163323f19b348f183b3d721b3688b2f90034185392"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SZRT3K3MIOHIDPNA5STEVVL4FL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ryota Miyano, Yuki Arase","submitted_at":"2025-05-30T03:34:25Z","abstract_excerpt":"This study proposes a simple yet effective LoRA merge method to achieve LLM adaptation for low-resource language generation tasks. The LoRA merge technique, which integrates multiple LoRA modules trained on different tasks, has gained attention as an effective and efficient approach for adapting LLMs to target tasks. However, previous methods are limited in adaptability as they keep the LoRA parameters frozen. Additionally, the low-resource problem has been out of their scope. We propose a LoRA merge method that updates and prunes LoRA parameters through fine-tuning with minimal target task da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24174","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/2505.24174/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":"2026-07-05T11:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxVKm2McCZXUVDPahXOTcTN8B1M3Gf+ghtiNcXtvY7q7Hm3jL0tJYhhD124RfNX2B3GRFIA0bPOImN53MWEHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:42:59.458956Z"},"content_sha256":"234d488a36ded58b7ea0658fbccfdad24c051b5e080accc53bb67a5758e68039","schema_version":"1.0","event_id":"sha256:234d488a36ded58b7ea0658fbccfdad24c051b5e080accc53bb67a5758e68039"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZRT3K3MIOHIDPNA5STEVVL4FL/bundle.json","state_url":"https://pith.science/pith/SZRT3K3MIOHIDPNA5STEVVL4FL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZRT3K3MIOHIDPNA5STEVVL4FL/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":"2026-08-08T11:42:59Z","links":{"resolver":"https://pith.science/pith/SZRT3K3MIOHIDPNA5STEVVL4FL","bundle":"https://pith.science/pith/SZRT3K3MIOHIDPNA5STEVVL4FL/bundle.json","state":"https://pith.science/pith/SZRT3K3MIOHIDPNA5STEVVL4FL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZRT3K3MIOHIDPNA5STEVVL4FL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SZRT3K3MIOHIDPNA5STEVVL4FL","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":"c406034d3654a10fdccbc1b97c4b931ea674c32cab10cd7aad965542380f6341","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T03:34:25Z","title_canon_sha256":"2161330610b997e9c9661f6da14b0cb97595dbe763d1a23946c30d330a967d09"},"schema_version":"1.0","source":{"id":"2505.24174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24174","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24174v1","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24174","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"SZRT3K3MIOHI","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_16","alias_value":"SZRT3K3MIOHIDPNA","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_8","alias_value":"SZRT3K3M","created_at":"2026-07-05T11:12:43Z"}],"graph_snapshots":[{"event_id":"sha256:234d488a36ded58b7ea0658fbccfdad24c051b5e080accc53bb67a5758e68039","target":"graph","created_at":"2026-07-05T11:12:43Z","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/2505.24174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study proposes a simple yet effective LoRA merge method to achieve LLM adaptation for low-resource language generation tasks. The LoRA merge technique, which integrates multiple LoRA modules trained on different tasks, has gained attention as an effective and efficient approach for adapting LLMs to target tasks. However, previous methods are limited in adaptability as they keep the LoRA parameters frozen. Additionally, the low-resource problem has been out of their scope. We propose a LoRA merge method that updates and prunes LoRA parameters through fine-tuning with minimal target task da","authors_text":"Ryota Miyano, Yuki Arase","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T03:34:25Z","title":"Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24174","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:d50cee73de895fc272a6cd163323f19b348f183b3d721b3688b2f90034185392","target":"record","created_at":"2026-07-05T11:12:43Z","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":"c406034d3654a10fdccbc1b97c4b931ea674c32cab10cd7aad965542380f6341","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T03:34:25Z","title_canon_sha256":"2161330610b997e9c9661f6da14b0cb97595dbe763d1a23946c30d330a967d09"},"schema_version":"1.0","source":{"id":"2505.24174","kind":"arxiv","version":1}},"canonical_sha256":"96633dab6c438e81bda0eca64ad57c2ae8562c50e72f6a4e7ab3ec44a9613684","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96633dab6c438e81bda0eca64ad57c2ae8562c50e72f6a4e7ab3ec44a9613684","first_computed_at":"2026-07-05T11:12:43.392172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:43.392172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2a2aUZOpe0g1eHRfYNJzXE9ZWfVvhDrxbn6owEO7+VqzRMZkbzZPWcyyLn/3y7au5fPlYPlFV5fZAQ/o43DSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:43.392740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d50cee73de895fc272a6cd163323f19b348f183b3d721b3688b2f90034185392","sha256:234d488a36ded58b7ea0658fbccfdad24c051b5e080accc53bb67a5758e68039"],"state_sha256":"7bfb206a7a7ca8418ce3c65e198d8505b7179bd75f54421c14b91f3809bd69ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dD/a8NfCNvCeJBO5gEElSJBtNcczswC1Wpg47odiCRtL8Ug2snBE96YzPi9w0qvXOxO4/xaKdacM+jePKvhcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:42:59.462678Z","bundle_sha256":"6c10650d3897cc0069c12dfa85449286e3eca9f92d65a24e0dc80d3a1ec51c4d"}}