{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LRW3GFUAQSOEPV3AHU4YLXJQJ5","short_pith_number":"pith:LRW3GFUA","schema_version":"1.0","canonical_sha256":"5c6db31680849c47d7603d3985dd304f47caed2ff492ce02b3c1b6b89d73d151","source":{"kind":"arxiv","id":"2502.04363","version":2},"attestation_state":"computed","paper":{"title":"On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bosung Kim, Isu Jeong, Jungmin Cheon, Kyuhwan Lee, Seulki Lee, Yeojin Lee","submitted_at":"2025-02-05T05:42:29Z","abstract_excerpt":"We present On-device Sora, the first model training-free solution for diffusion-based on-device text-to-video generation that operates efficiently on smartphone-grade devices. To address the challenges of diffusion-based text-to-video generation on computation- and memory-limited mobile devices, the proposed On-device Sora applies three novel techniques to pre-trained video generative models. First, Linear Proportional Leap (LPL) reduces the excessive denoising steps required in video diffusion through an efficient leap-based approach. Second, Temporal Dimension Token Merging (TDTM) minimizes "},"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":"2502.04363","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-05T05:42:29Z","cross_cats_sorted":[],"title_canon_sha256":"81d0f493caec9360104aa55d06acc409836b8ded545329b149f5f53b0cbc0994","abstract_canon_sha256":"14516101fd31a436fb1c0c7ad336f1155130942cc5390bae6bdd7ba597bda990"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:52.385903Z","signature_b64":"WU93nx/jM3ITbi9GGIJJRlA4d+qBtcDyg88OewWtoVxzAIKcwQlmbXn49QlulXlzppQdk1ksmqedZoSpAo4UBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c6db31680849c47d7603d3985dd304f47caed2ff492ce02b3c1b6b89d73d151","last_reissued_at":"2026-07-05T10:41:52.385273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:52.385273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bosung Kim, Isu Jeong, Jungmin Cheon, Kyuhwan Lee, Seulki Lee, Yeojin Lee","submitted_at":"2025-02-05T05:42:29Z","abstract_excerpt":"We present On-device Sora, the first model training-free solution for diffusion-based on-device text-to-video generation that operates efficiently on smartphone-grade devices. To address the challenges of diffusion-based text-to-video generation on computation- and memory-limited mobile devices, the proposed On-device Sora applies three novel techniques to pre-trained video generative models. First, Linear Proportional Leap (LPL) reduces the excessive denoising steps required in video diffusion through an efficient leap-based approach. Second, Temporal Dimension Token Merging (TDTM) minimizes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04363","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/2502.04363/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":"2502.04363","created_at":"2026-07-05T10:41:52.385352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04363v2","created_at":"2026-07-05T10:41:52.385352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04363","created_at":"2026-07-05T10:41:52.385352+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRW3GFUAQSOE","created_at":"2026-07-05T10:41:52.385352+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRW3GFUAQSOEPV3A","created_at":"2026-07-05T10:41:52.385352+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRW3GFUA","created_at":"2026-07-05T10:41:52.385352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06173","citing_title":"MobileWan: Closing the Quality Gap for Mobile Video Diffusion","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5","json":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5.json","graph_json":"https://pith.science/api/pith-number/LRW3GFUAQSOEPV3AHU4YLXJQJ5/graph.json","events_json":"https://pith.science/api/pith-number/LRW3GFUAQSOEPV3AHU4YLXJQJ5/events.json","paper":"https://pith.science/paper/LRW3GFUA"},"agent_actions":{"view_html":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5","download_json":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5.json","view_paper":"https://pith.science/paper/LRW3GFUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04363&json=true","fetch_graph":"https://pith.science/api/pith-number/LRW3GFUAQSOEPV3AHU4YLXJQJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/LRW3GFUAQSOEPV3AHU4YLXJQJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5/action/storage_attestation","attest_author":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5/action/author_attestation","sign_citation":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5/action/citation_signature","submit_replication":"https://pith.science/pith/LRW3GFUAQSOEPV3AHU4YLXJQJ5/action/replication_record"}},"created_at":"2026-07-05T10:41:52.385352+00:00","updated_at":"2026-07-05T10:41:52.385352+00:00"}