{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6JX6RVXPKN5GVN75IT7RQGVPFO","short_pith_number":"pith:6JX6RVXP","schema_version":"1.0","canonical_sha256":"f26fe8d6ef537a6ab7fd44ff181aaf2ba1561f084b7033dbabf0dae5612c2ab9","source":{"kind":"arxiv","id":"2503.08741","version":3},"attestation_state":"computed","paper":{"title":"Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingchen Zhao, Cheng Yang, Letian Zhang, Quan Cui","submitted_at":"2025-03-11T08:25:40Z","abstract_excerpt":"The success of multi-modal large language models (MLLMs) has been largely attributed to the large-scale training data. However, the training data of many MLLMs is unavailable due to privacy concerns. The expensive and labor-intensive process of collecting multi-modal data further exacerbates the problem. Is it possible to synthesize multi-modal training data automatically without compromising diversity and quality? In this paper, we propose a new method, Oasis, to synthesize high-quality multi-modal data with only images. Oasis breaks through traditional methods by prompting only images to the"},"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":"2503.08741","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T08:25:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"750225b3fefe74c9cdc0d06dbaa546627d96f550a40f28288730e058d406f3a7","abstract_canon_sha256":"3cbff4839b2e564ea021f3601e0b3573c856327cb57b03d66da7a3fee0c3cae2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:26.920874Z","signature_b64":"pkpz8GQHmv5NtMcjBp6v+6za4llXYWsu5uQgsYUUOCWM6UNuiVM9JUALIujB1CWnaDHIr0HCliHznbr5LNk0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f26fe8d6ef537a6ab7fd44ff181aaf2ba1561f084b7033dbabf0dae5612c2ab9","last_reissued_at":"2026-07-05T10:39:26.920397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:26.920397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingchen Zhao, Cheng Yang, Letian Zhang, Quan Cui","submitted_at":"2025-03-11T08:25:40Z","abstract_excerpt":"The success of multi-modal large language models (MLLMs) has been largely attributed to the large-scale training data. However, the training data of many MLLMs is unavailable due to privacy concerns. The expensive and labor-intensive process of collecting multi-modal data further exacerbates the problem. Is it possible to synthesize multi-modal training data automatically without compromising diversity and quality? In this paper, we propose a new method, Oasis, to synthesize high-quality multi-modal data with only images. Oasis breaks through traditional methods by prompting only images to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08741","kind":"arxiv","version":3},"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/2503.08741/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":"2503.08741","created_at":"2026-07-05T10:39:26.920453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08741v3","created_at":"2026-07-05T10:39:26.920453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08741","created_at":"2026-07-05T10:39:26.920453+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JX6RVXPKN5G","created_at":"2026-07-05T10:39:26.920453+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JX6RVXPKN5GVN75","created_at":"2026-07-05T10:39:26.920453+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JX6RVXP","created_at":"2026-07-05T10:39:26.920453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21893","citing_title":"Aether Weaver: Multimodal Affective Narrative Co-Generation with Dynamic Scene Graphs","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO","json":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO.json","graph_json":"https://pith.science/api/pith-number/6JX6RVXPKN5GVN75IT7RQGVPFO/graph.json","events_json":"https://pith.science/api/pith-number/6JX6RVXPKN5GVN75IT7RQGVPFO/events.json","paper":"https://pith.science/paper/6JX6RVXP"},"agent_actions":{"view_html":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO","download_json":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO.json","view_paper":"https://pith.science/paper/6JX6RVXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08741&json=true","fetch_graph":"https://pith.science/api/pith-number/6JX6RVXPKN5GVN75IT7RQGVPFO/graph.json","fetch_events":"https://pith.science/api/pith-number/6JX6RVXPKN5GVN75IT7RQGVPFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO/action/storage_attestation","attest_author":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO/action/author_attestation","sign_citation":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO/action/citation_signature","submit_replication":"https://pith.science/pith/6JX6RVXPKN5GVN75IT7RQGVPFO/action/replication_record"}},"created_at":"2026-07-05T10:39:26.920453+00:00","updated_at":"2026-07-05T10:39:26.920453+00:00"}