{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XSJNXPYWJ45I74NGMDDCY6B73N","short_pith_number":"pith:XSJNXPYW","schema_version":"1.0","canonical_sha256":"bc92dbbf164f3a8ff1a660c62c783fdb7106851c3a8d51a953980706da6fd00f","source":{"kind":"arxiv","id":"2503.10406","version":2},"attestation_state":"computed","paper":{"title":"RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mengqi Huang, Shuhan Zhuang, Yijing Lin, Zhendong Mao","submitted_at":"2025-03-13T14:31:52Z","abstract_excerpt":"Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual generation models fail to meet these principles. Current approaches either rely on per-task datasets and large-scale training or adapt pre-trained image models with task-specific modifications, limiting their generalizability. In this work, we explore video models as a foundation for unified image generation, leveraging their inherent ability to model temporal cor"},"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":"2503.10406","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T14:31:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71bdec1191ad4c5b8a67721bd9ec8e9d7c7fad3dbcdfadcca0317ca335d7b5ca","abstract_canon_sha256":"5151fb899f85b664fdea338ac338b98ae4afec64f05d60ee7978c861a8f8d115"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:50.744328Z","signature_b64":"ln1Mn0KOkmy8KWAdyfYJmICtcdHunhzT7znMhzXAPMuw4p0YisWkM+/u4nAjG7UOlPpCdk4Ivt4pk011V9QsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc92dbbf164f3a8ff1a660c62c783fdb7106851c3a8d51a953980706da6fd00f","last_reissued_at":"2026-07-05T11:39:50.743750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:50.743750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mengqi Huang, Shuhan Zhuang, Yijing Lin, Zhendong Mao","submitted_at":"2025-03-13T14:31:52Z","abstract_excerpt":"Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual generation models fail to meet these principles. Current approaches either rely on per-task datasets and large-scale training or adapt pre-trained image models with task-specific modifications, limiting their generalizability. In this work, we explore video models as a foundation for unified image generation, leveraging their inherent ability to model temporal cor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10406","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/2503.10406/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":"2503.10406","created_at":"2026-07-05T11:39:50.743811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10406v2","created_at":"2026-07-05T11:39:50.743811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10406","created_at":"2026-07-05T11:39:50.743811+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSJNXPYWJ45I","created_at":"2026-07-05T11:39:50.743811+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSJNXPYWJ45I74NG","created_at":"2026-07-05T11:39:50.743811+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSJNXPYW","created_at":"2026-07-05T11:39:50.743811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.20328","citing_title":"Video models are zero-shot learners and reasoners","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N","json":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N.json","graph_json":"https://pith.science/api/pith-number/XSJNXPYWJ45I74NGMDDCY6B73N/graph.json","events_json":"https://pith.science/api/pith-number/XSJNXPYWJ45I74NGMDDCY6B73N/events.json","paper":"https://pith.science/paper/XSJNXPYW"},"agent_actions":{"view_html":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N","download_json":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N.json","view_paper":"https://pith.science/paper/XSJNXPYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10406&json=true","fetch_graph":"https://pith.science/api/pith-number/XSJNXPYWJ45I74NGMDDCY6B73N/graph.json","fetch_events":"https://pith.science/api/pith-number/XSJNXPYWJ45I74NGMDDCY6B73N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N/action/storage_attestation","attest_author":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N/action/author_attestation","sign_citation":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N/action/citation_signature","submit_replication":"https://pith.science/pith/XSJNXPYWJ45I74NGMDDCY6B73N/action/replication_record"}},"created_at":"2026-07-05T11:39:50.743811+00:00","updated_at":"2026-07-05T11:39:50.743811+00:00"}