{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E6M3GHPR6ICPFAXAWGNBK6W6M7","short_pith_number":"pith:E6M3GHPR","schema_version":"1.0","canonical_sha256":"2799b31df1f204f282e0b19a157ade67e7ac5626e80e8b68475414ddeea16e09","source":{"kind":"arxiv","id":"2311.10702","version":2},"attestation_state":"computed","paper":{"title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Wadden, Hamish Ivison, Hannaneh Hajishirzi, Iz Beltagy, Joel Jang, Matthew Peters, Nathan Lambert, Noah A. Smith, Pradeep Dasigi, Valentina Pyatkin, Yizhong Wang","submitted_at":"2023-11-17T18:45:45Z","abstract_excerpt":"Since the release of T\\\"ULU [Wang et al., 2023b], open resources for instruction tuning have developed quickly, from better base models to new finetuning techniques. We test and incorporate a number of these advances into T\\\"ULU, resulting in T\\\"ULU 2, a suite of improved T\\\"ULU models for advancing the understanding and best practices of adapting pretrained language models to downstream tasks and user preferences. Concretely, we release: (1) T\\\"ULU-V2-mix, an improved collection of high-quality instruction datasets; (2) T\\\"ULU 2, LLAMA-2 models finetuned on the V2 mixture; (3) T\\\"ULU 2+DPO, T"},"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":"2311.10702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-17T18:45:45Z","cross_cats_sorted":[],"title_canon_sha256":"a5a250369cba1ad0849c040980ab981e6dce720c70d93918880def6c87f5b32e","abstract_canon_sha256":"6625b39ad7aaca8542971f9ba997f1b44ac1a1b8e63e9ba97b67755c2ed4d1d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:22.033027Z","signature_b64":"hj83hCUkg8p00BigFFw0fSq6rZXvaY64rBCDfT15LHwz7k6r4UQCE2m1WtkCcJlKtb7RUTeMoZ2xWXhB6pAoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2799b31df1f204f282e0b19a157ade67e7ac5626e80e8b68475414ddeea16e09","last_reissued_at":"2026-07-05T07:14:22.032470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:22.032470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Wadden, Hamish Ivison, Hannaneh Hajishirzi, Iz Beltagy, Joel Jang, Matthew Peters, Nathan Lambert, Noah A. Smith, Pradeep Dasigi, Valentina Pyatkin, Yizhong Wang","submitted_at":"2023-11-17T18:45:45Z","abstract_excerpt":"Since the release of T\\\"ULU [Wang et al., 2023b], open resources for instruction tuning have developed quickly, from better base models to new finetuning techniques. We test and incorporate a number of these advances into T\\\"ULU, resulting in T\\\"ULU 2, a suite of improved T\\\"ULU models for advancing the understanding and best practices of adapting pretrained language models to downstream tasks and user preferences. Concretely, we release: (1) T\\\"ULU-V2-mix, an improved collection of high-quality instruction datasets; (2) T\\\"ULU 2, LLAMA-2 models finetuned on the V2 mixture; (3) T\\\"ULU 2+DPO, T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10702","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/2311.10702/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":"2311.10702","created_at":"2026-07-05T07:14:22.032532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10702v2","created_at":"2026-07-05T07:14:22.032532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10702","created_at":"2026-07-05T07:14:22.032532+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6M3GHPR6ICP","created_at":"2026-07-05T07:14:22.032532+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6M3GHPR6ICPFAXA","created_at":"2026-07-05T07:14:22.032532+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6M3GHPR","created_at":"2026-07-05T07:14:22.032532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30814","citing_title":"When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28373","citing_title":"Model Merging to Evolution: Parameter Space Exploration for Expert Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29295","citing_title":"EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2504.12501","citing_title":"Reinforcement Learning from Human Feedback","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12773","citing_title":"Dr.LLM: Dynamic Layer Routing in LLMs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20834","citing_title":"Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07111","citing_title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19018","citing_title":"LoRA vs. Full Fine-Tuning: A Theoretical Perspective","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02833","citing_title":"Generalizing Verifiable Instruction Following","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23542","citing_title":"On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2406.11794","citing_title":"DataComp-LM: In search of the next generation of training sets for language models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08464","citing_title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21362","citing_title":"AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10468","citing_title":"Can Muon Fine-tune Adam-Pretrained Models?","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07111","citing_title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04291","citing_title":"Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7","json":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7.json","graph_json":"https://pith.science/api/pith-number/E6M3GHPR6ICPFAXAWGNBK6W6M7/graph.json","events_json":"https://pith.science/api/pith-number/E6M3GHPR6ICPFAXAWGNBK6W6M7/events.json","paper":"https://pith.science/paper/E6M3GHPR"},"agent_actions":{"view_html":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7","download_json":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7.json","view_paper":"https://pith.science/paper/E6M3GHPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10702&json=true","fetch_graph":"https://pith.science/api/pith-number/E6M3GHPR6ICPFAXAWGNBK6W6M7/graph.json","fetch_events":"https://pith.science/api/pith-number/E6M3GHPR6ICPFAXAWGNBK6W6M7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7/action/storage_attestation","attest_author":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7/action/author_attestation","sign_citation":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7/action/citation_signature","submit_replication":"https://pith.science/pith/E6M3GHPR6ICPFAXAWGNBK6W6M7/action/replication_record"}},"created_at":"2026-07-05T07:14:22.032532+00:00","updated_at":"2026-07-05T07:14:22.032532+00:00"}