{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YQS2S3KOYSXNGK7ZD6BXLDGYSJ","short_pith_number":"pith:YQS2S3KO","schema_version":"1.0","canonical_sha256":"c425a96d4ec4aed32bf91f83758cd89264e71a5da907800c32f1f9647166b6ac","source":{"kind":"arxiv","id":"2408.05517","version":4},"attestation_state":"computed","paper":{"title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ang Wang, Baole Ai, Daoze Zhang, Hong Zhang, Jinghan Hu, Jintao Huang, Wenmeng Zhou, Xingjun Wang, Yingda Chen, Yunlin Mao, Yuze Zhao, Zeyinzi Jiang, Zhikai Wu","submitted_at":"2024-08-10T11:00:13Z","abstract_excerpt":"Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since covered extensive areas of traditional learning tasks. For instance, text-based tasks such as text-classification and sequence-labeling, as well as multi-modal tasks like Visual Question Answering (VQA) and Optical Character Recognition (OCR), which were previously addressed using different models, can now be tackled based on one foundation model. Consequently, "},"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":"2408.05517","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T11:00:13Z","cross_cats_sorted":[],"title_canon_sha256":"f50c362e17b91db34d0b2fc28559e718a5a6ba438b63c01edda5d0b7fa33d253","abstract_canon_sha256":"8ba2221d7eddb1767f08e4fdb701328339f3aea369ad442f9ec57285ccdb5c15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:39.021942Z","signature_b64":"wFzvbRYx0tWo9B138Y44g+TBMA4S8/hP1m8wg8tCI86ObK9H1bgFI9Fk8uSzcyi/8ZP1kVII8Nb3cPE/I4jMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c425a96d4ec4aed32bf91f83758cd89264e71a5da907800c32f1f9647166b6ac","last_reissued_at":"2026-07-05T11:04:39.021388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:39.021388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ang Wang, Baole Ai, Daoze Zhang, Hong Zhang, Jinghan Hu, Jintao Huang, Wenmeng Zhou, Xingjun Wang, Yingda Chen, Yunlin Mao, Yuze Zhao, Zeyinzi Jiang, Zhikai Wu","submitted_at":"2024-08-10T11:00:13Z","abstract_excerpt":"Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since covered extensive areas of traditional learning tasks. For instance, text-based tasks such as text-classification and sequence-labeling, as well as multi-modal tasks like Visual Question Answering (VQA) and Optical Character Recognition (OCR), which were previously addressed using different models, can now be tackled based on one foundation model. Consequently, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05517","kind":"arxiv","version":4},"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/2408.05517/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":"2408.05517","created_at":"2026-07-05T11:04:39.021447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05517v4","created_at":"2026-07-05T11:04:39.021447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05517","created_at":"2026-07-05T11:04:39.021447+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQS2S3KOYSXN","created_at":"2026-07-05T11:04:39.021447+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQS2S3KOYSXNGK7Z","created_at":"2026-07-05T11:04:39.021447+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQS2S3KO","created_at":"2026-07-05T11:04:39.021447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18483","citing_title":"Steadily moving semi-infinite fracture in plane poroelasticity","ref_index":115,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00260","citing_title":"Do Multimodal Large Language Models Need Reasoning to Classify Dementia from Speech?","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12817","citing_title":"Teach-and-Repeat: Accurately Extracting Operational Knowledge from Mobile Screen Demonstrations to Empower GUI Agents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08952","citing_title":"AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00260","citing_title":"Do Multimodal Large Language Models Need Reasoning to Classify Dementia from Speech?","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04591","citing_title":"Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27190","citing_title":"Learning When to Think While Listening in Large Audio-Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28091","citing_title":"Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29523","citing_title":"K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30639","citing_title":"PInVerify: An Offline Embodied Benchmark for Active Instance Verification","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30219","citing_title":"When Should Models Change Their Minds? Contextual Belief Management in Large Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00755","citing_title":"Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22655","citing_title":"Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22501","citing_title":"BeLink: Biomedical Entity Linking Meets Generative Re-Ranking","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21996","citing_title":"From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21295","citing_title":"TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2512.11013","citing_title":"PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2512.11321","citing_title":"KeyframeFace: Language-Driven Facial Animation via Semantic Keyframes","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20375","citing_title":"LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09677","citing_title":"Logics-Parsing-Omni Technical Report","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04005","citing_title":"Domain-Adaptive Dense Retrieval for Brazilian Legal Search","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09996","citing_title":"Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07177","citing_title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04018","citing_title":"Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07872","citing_title":"Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ","json":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ.json","graph_json":"https://pith.science/api/pith-number/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/graph.json","events_json":"https://pith.science/api/pith-number/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/events.json","paper":"https://pith.science/paper/YQS2S3KO"},"agent_actions":{"view_html":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ","download_json":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ.json","view_paper":"https://pith.science/paper/YQS2S3KO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05517&json=true","fetch_graph":"https://pith.science/api/pith-number/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/action/storage_attestation","attest_author":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/action/author_attestation","sign_citation":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/action/citation_signature","submit_replication":"https://pith.science/pith/YQS2S3KOYSXNGK7ZD6BXLDGYSJ/action/replication_record"}},"created_at":"2026-07-05T11:04:39.021447+00:00","updated_at":"2026-07-05T11:04:39.021447+00:00"}