{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7JIWQ2WPLZILLCKVVKMU72BVFG","short_pith_number":"pith:7JIWQ2WP","schema_version":"1.0","canonical_sha256":"fa51686acf5e50b58955aa994fe835298000ca32c3d5893df08e4d31175f0431","source":{"kind":"arxiv","id":"2506.06105","version":2},"attestation_state":"computed","paper":{"title":"Text-to-LoRA: Instant Transformer Adaption","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Edoardo Cetin, Robert Tjarko Lange, Rujikorn Charakorn, Yujin Tang","submitted_at":"2025-06-06T14:11:27Z","abstract_excerpt":"While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model. Fine-tuning techniques enable practitioners to adapt foundation models for many new applications but require expensive and lengthy training while being notably sensitive to hyperparameter choices. To overcome these limitations, we introduce Text-to-LoRA (T2L), a model capable of adapting large language models (LLMs) on the fly solely based on a natural lang"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.06105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T14:11:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34e7053eb2642b22494126ae0763b7dc60a2c17e918dc363d5e66e75e794174a","abstract_canon_sha256":"6e45a9d83a689a8e2882b14fb70a6d0bacbd569421e017d43ad48b2e987ba4dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:23.766217Z","signature_b64":"jDa2IVzHO5dXndNCvXNnghygkUdGp56jaUIdJqdWIFFqCfFoouXmS09OwaMQKujIFxhXmQdvI5hnErjNEbcPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa51686acf5e50b58955aa994fe835298000ca32c3d5893df08e4d31175f0431","last_reissued_at":"2026-07-05T11:18:23.765729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:23.765729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-to-LoRA: Instant Transformer Adaption","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Edoardo Cetin, Robert Tjarko Lange, Rujikorn Charakorn, Yujin Tang","submitted_at":"2025-06-06T14:11:27Z","abstract_excerpt":"While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model. Fine-tuning techniques enable practitioners to adapt foundation models for many new applications but require expensive and lengthy training while being notably sensitive to hyperparameter choices. To overcome these limitations, we introduce Text-to-LoRA (T2L), a model capable of adapting large language models (LLMs) on the fly solely based on a natural lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06105","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/2506.06105/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.06105","created_at":"2026-07-05T11:18:23.765792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06105v2","created_at":"2026-07-05T11:18:23.765792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06105","created_at":"2026-07-05T11:18:23.765792+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JIWQ2WPLZIL","created_at":"2026-07-05T11:18:23.765792+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JIWQ2WPLZILLCKV","created_at":"2026-07-05T11:18:23.765792+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JIWQ2WP","created_at":"2026-07-05T11:18:23.765792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05300","citing_title":"Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19172","citing_title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12942","citing_title":"PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13971","citing_title":"Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07217","citing_title":"Robotic Policy Adaptation via Weight-Space Meta-Learning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02609","citing_title":"Building Better Activation Oracles","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30015","citing_title":"Parametric Skills","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13919","citing_title":"Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20189","citing_title":"SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18226","citing_title":"Context Memorization for Efficient Long Context Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18474","citing_title":"Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14055","citing_title":"PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23750","citing_title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09778","citing_title":"Nectar: Neural Estimation of Cached-Token Attention via Regression","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23750","citing_title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG","json":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG.json","graph_json":"https://pith.science/api/pith-number/7JIWQ2WPLZILLCKVVKMU72BVFG/graph.json","events_json":"https://pith.science/api/pith-number/7JIWQ2WPLZILLCKVVKMU72BVFG/events.json","paper":"https://pith.science/paper/7JIWQ2WP"},"agent_actions":{"view_html":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG","download_json":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG.json","view_paper":"https://pith.science/paper/7JIWQ2WP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06105&json=true","fetch_graph":"https://pith.science/api/pith-number/7JIWQ2WPLZILLCKVVKMU72BVFG/graph.json","fetch_events":"https://pith.science/api/pith-number/7JIWQ2WPLZILLCKVVKMU72BVFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG/action/storage_attestation","attest_author":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG/action/author_attestation","sign_citation":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG/action/citation_signature","submit_replication":"https://pith.science/pith/7JIWQ2WPLZILLCKVVKMU72BVFG/action/replication_record"}},"created_at":"2026-07-05T11:18:23.765792+00:00","updated_at":"2026-07-05T11:18:23.765792+00:00"}