{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YE54OFGZ23CS47X2EHLNYWZHG3","short_pith_number":"pith:YE54OFGZ","canonical_record":{"source":{"id":"2506.11638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T10:11:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ddc47a39f72245608e7fb23f89cc81dbed6050313557d7f7e00d77b94ba0f9d7","abstract_canon_sha256":"5d3d274ddc691b77da5609479e4ccbf52c6192672d64967826b8efd6d4c5a92a"},"schema_version":"1.0"},"canonical_sha256":"c13bc714d9d6c52e7efa21d6dc5b2736fd8df848feb96a3bf29b3a8241c80aeb","source":{"kind":"arxiv","id":"2506.11638","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11638","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11638v1","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11638","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"YE54OFGZ23CS","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"YE54OFGZ23CS47X2","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"YE54OFGZ","created_at":"2026-07-05T11:21:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YE54OFGZ23CS47X2EHLNYWZHG3","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T10:11:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ddc47a39f72245608e7fb23f89cc81dbed6050313557d7f7e00d77b94ba0f9d7","abstract_canon_sha256":"5d3d274ddc691b77da5609479e4ccbf52c6192672d64967826b8efd6d4c5a92a"},"schema_version":"1.0"},"canonical_sha256":"c13bc714d9d6c52e7efa21d6dc5b2736fd8df848feb96a3bf29b3a8241c80aeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:08.081916Z","signature_b64":"6dhxrLsCDJWa/fe4NRHfuST8IMx1158DarD11CKnu8wn06BSh9/KIPKAuI54vJB+qM1/KvzUIYG3B2bPljq2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c13bc714d9d6c52e7efa21d6dc5b2736fd8df848feb96a3bf29b3a8241c80aeb","last_reissued_at":"2026-07-05T11:21:08.081458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:08.081458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11638","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":"2026-07-05T11:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iN060r6gCElFCTf1fJIDSvUCL6Pa3d+WcL1HsLYia2Qudj2Wn8Th7Veu4bVF1Dub6xwenwGRXZQ3EYDZV4N/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:29.654546Z"},"content_sha256":"076cb5606a9e14d27459649f62c4ea5768e293c4eecd93a5b5d3e7cfdf0f54da","schema_version":"1.0","event_id":"sha256:076cb5606a9e14d27459649f62c4ea5768e293c4eecd93a5b5d3e7cfdf0f54da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YE54OFGZ23CS47X2EHLNYWZHG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoRA-Gen: Specializing Large Language Model via Online LoRA Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng cheng, Lin Song, Rui Yang, Xiu Li, Yicheng Xiao, Ying Shan, Yixiao Ge","submitted_at":"2025-06-13T10:11:01Z","abstract_excerpt":"Recent advances have highlighted the benefits of scaling language models to enhance performance across a wide range of NLP tasks. However, these approaches still face limitations in effectiveness and efficiency when applied to domain-specific tasks, particularly for small edge-side models. We propose the LoRA-Gen framework, which utilizes a large cloud-side model to generate LoRA parameters for edge-side models based on task descriptions. By employing the reparameterization technique, we merge the LoRA parameters into the edge-side model to achieve flexible specialization. Our method facilitat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11638","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/2506.11638/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":"2026-07-05T11:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjeOvCWJqHx4MN2Sm0I8b3aX+VP6k8dd2MTBlsSAI32cgw1B20uw8GEq4fcvOj6V6GPbkgquMx9U3J93dCisCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:29.654942Z"},"content_sha256":"030f2bf2ebb39c871b6c8aaa4afc62970f07ac555813cac6e04c2695e77cadee","schema_version":"1.0","event_id":"sha256:030f2bf2ebb39c871b6c8aaa4afc62970f07ac555813cac6e04c2695e77cadee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YE54OFGZ23CS47X2EHLNYWZHG3/bundle.json","state_url":"https://pith.science/pith/YE54OFGZ23CS47X2EHLNYWZHG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YE54OFGZ23CS47X2EHLNYWZHG3/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":"2026-07-08T19:10:29Z","links":{"resolver":"https://pith.science/pith/YE54OFGZ23CS47X2EHLNYWZHG3","bundle":"https://pith.science/pith/YE54OFGZ23CS47X2EHLNYWZHG3/bundle.json","state":"https://pith.science/pith/YE54OFGZ23CS47X2EHLNYWZHG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YE54OFGZ23CS47X2EHLNYWZHG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YE54OFGZ23CS47X2EHLNYWZHG3","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":"5d3d274ddc691b77da5609479e4ccbf52c6192672d64967826b8efd6d4c5a92a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T10:11:01Z","title_canon_sha256":"ddc47a39f72245608e7fb23f89cc81dbed6050313557d7f7e00d77b94ba0f9d7"},"schema_version":"1.0","source":{"id":"2506.11638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11638","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11638v1","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11638","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"YE54OFGZ23CS","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"YE54OFGZ23CS47X2","created_at":"2026-07-05T11:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"YE54OFGZ","created_at":"2026-07-05T11:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:030f2bf2ebb39c871b6c8aaa4afc62970f07ac555813cac6e04c2695e77cadee","target":"graph","created_at":"2026-07-05T11:21:08Z","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/2506.11638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances have highlighted the benefits of scaling language models to enhance performance across a wide range of NLP tasks. However, these approaches still face limitations in effectiveness and efficiency when applied to domain-specific tasks, particularly for small edge-side models. We propose the LoRA-Gen framework, which utilizes a large cloud-side model to generate LoRA parameters for edge-side models based on task descriptions. By employing the reparameterization technique, we merge the LoRA parameters into the edge-side model to achieve flexible specialization. Our method facilitat","authors_text":"Cheng cheng, Lin Song, Rui Yang, Xiu Li, Yicheng Xiao, Ying Shan, Yixiao Ge","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T10:11:01Z","title":"LoRA-Gen: Specializing Large Language Model via Online LoRA Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11638","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":"sha256:076cb5606a9e14d27459649f62c4ea5768e293c4eecd93a5b5d3e7cfdf0f54da","target":"record","created_at":"2026-07-05T11:21:08Z","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":"5d3d274ddc691b77da5609479e4ccbf52c6192672d64967826b8efd6d4c5a92a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T10:11:01Z","title_canon_sha256":"ddc47a39f72245608e7fb23f89cc81dbed6050313557d7f7e00d77b94ba0f9d7"},"schema_version":"1.0","source":{"id":"2506.11638","kind":"arxiv","version":1}},"canonical_sha256":"c13bc714d9d6c52e7efa21d6dc5b2736fd8df848feb96a3bf29b3a8241c80aeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c13bc714d9d6c52e7efa21d6dc5b2736fd8df848feb96a3bf29b3a8241c80aeb","first_computed_at":"2026-07-05T11:21:08.081458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:08.081458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6dhxrLsCDJWa/fe4NRHfuST8IMx1158DarD11CKnu8wn06BSh9/KIPKAuI54vJB+qM1/KvzUIYG3B2bPljq2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:08.081916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:076cb5606a9e14d27459649f62c4ea5768e293c4eecd93a5b5d3e7cfdf0f54da","sha256:030f2bf2ebb39c871b6c8aaa4afc62970f07ac555813cac6e04c2695e77cadee"],"state_sha256":"594aeec50d226b9bec766b0609be57c66dc0f9731c9bce615e6370dfef807bcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6s9KYMHve81gm49m4SIZaCXtUbHB+rs0OQU9POLlhlVFBemoHucGvpjR5NyAiCAlmVPTS9dFIYvxV8t8aNlyDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:10:29.657080Z","bundle_sha256":"dd40fb60de235ce8b5348c3a0b4c48772e66bfdb7874a3e48feb59a527526b3d"}}