{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4IQOVV4GGZQ2EQZ3SJEO5YTMYU","short_pith_number":"pith:4IQOVV4G","schema_version":"1.0","canonical_sha256":"e220ead7863661a2433b9248eee26cc503532ff28a47fe0a9d036a7400311909","source":{"kind":"arxiv","id":"2406.01843","version":1},"attestation_state":"computed","paper":{"title":"L-MAGIC: Language Model Assisted Generation of Images with Coherence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diana Wofk, Gabriela Ben-Melech Stan, Junda Cheng, Matthias Mueller, Michael Paulitsch, Reiner Birkl, Shao-Yen Tseng, Vasudev Lal, Zhipeng Cai","submitted_at":"2024-06-03T23:28:57Z","abstract_excerpt":"In the current era of generative AI breakthroughs, generating panoramic scenes from a single input image remains a key challenge. Most existing methods use diffusion-based iterative or simultaneous multi-view inpainting. However, the lack of global scene layout priors leads to subpar outputs with duplicated objects (e.g., multiple beds in a bedroom) or requires time-consuming human text inputs for each view. We propose L-MAGIC, a novel method leveraging large language models for guidance while diffusing multiple coherent views of 360 degree panoramic scenes. L-MAGIC harnesses pre-trained diffu"},"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":"2406.01843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T23:28:57Z","cross_cats_sorted":[],"title_canon_sha256":"eca42566cce8d8ca94d2f9126cf9476ae8b2b859fa317951c6d06378099aa8af","abstract_canon_sha256":"722b14d99c4e3abe0f4f8a90d8e8391696403d10d72b9ac25363f6055adf1558"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:49.434569Z","signature_b64":"8F/X6chkaHkTDclDhooVprZCWkpB2Br51ATTB/AiBfPwlhvSbLgwCwwzzKuUIhjtg4jaOgbjtnfYf9yoLZJgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e220ead7863661a2433b9248eee26cc503532ff28a47fe0a9d036a7400311909","last_reissued_at":"2026-07-05T08:26:49.434189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:49.434189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L-MAGIC: Language Model Assisted Generation of Images with Coherence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diana Wofk, Gabriela Ben-Melech Stan, Junda Cheng, Matthias Mueller, Michael Paulitsch, Reiner Birkl, Shao-Yen Tseng, Vasudev Lal, Zhipeng Cai","submitted_at":"2024-06-03T23:28:57Z","abstract_excerpt":"In the current era of generative AI breakthroughs, generating panoramic scenes from a single input image remains a key challenge. Most existing methods use diffusion-based iterative or simultaneous multi-view inpainting. However, the lack of global scene layout priors leads to subpar outputs with duplicated objects (e.g., multiple beds in a bedroom) or requires time-consuming human text inputs for each view. We propose L-MAGIC, a novel method leveraging large language models for guidance while diffusing multiple coherent views of 360 degree panoramic scenes. L-MAGIC harnesses pre-trained diffu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01843","kind":"arxiv","version":1},"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/2406.01843/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":"2406.01843","created_at":"2026-07-05T08:26:49.434244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01843v1","created_at":"2026-07-05T08:26:49.434244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01843","created_at":"2026-07-05T08:26:49.434244+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IQOVV4GGZQ2","created_at":"2026-07-05T08:26:49.434244+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IQOVV4GGZQ2EQZ3","created_at":"2026-07-05T08:26:49.434244+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IQOVV4G","created_at":"2026-07-05T08:26:49.434244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU","json":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU.json","graph_json":"https://pith.science/api/pith-number/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/graph.json","events_json":"https://pith.science/api/pith-number/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/events.json","paper":"https://pith.science/paper/4IQOVV4G"},"agent_actions":{"view_html":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU","download_json":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU.json","view_paper":"https://pith.science/paper/4IQOVV4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01843&json=true","fetch_graph":"https://pith.science/api/pith-number/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/graph.json","fetch_events":"https://pith.science/api/pith-number/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/action/storage_attestation","attest_author":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/action/author_attestation","sign_citation":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/action/citation_signature","submit_replication":"https://pith.science/pith/4IQOVV4GGZQ2EQZ3SJEO5YTMYU/action/replication_record"}},"created_at":"2026-07-05T08:26:49.434244+00:00","updated_at":"2026-07-05T08:26:49.434244+00:00"}