{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LNLZP6WZ3DODC7VNYVSH2JSBQ2","short_pith_number":"pith:LNLZP6WZ","canonical_record":{"source":{"id":"2504.08641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T15:41:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"038528a8e1d7ed7122b115838b33287e00031d7632d1a07c06cc19e333b0540d","abstract_canon_sha256":"ec14c3370ae41ea1263c0f94f8105c0b31c11fb69e2ec549b78b40d542246db4"},"schema_version":"1.0"},"canonical_sha256":"5b5797fad9d8dc317eadc5647d264186904b8b61dea66312eb962a523c996ba1","source":{"kind":"arxiv","id":"2504.08641","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08641","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08641v1","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08641","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"LNLZP6WZ3DOD","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"LNLZP6WZ3DODC7VN","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"LNLZP6WZ","created_at":"2026-07-05T10:47:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LNLZP6WZ3DODC7VNYVSH2JSBQ2","target":"record","payload":{"canonical_record":{"source":{"id":"2504.08641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T15:41:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"038528a8e1d7ed7122b115838b33287e00031d7632d1a07c06cc19e333b0540d","abstract_canon_sha256":"ec14c3370ae41ea1263c0f94f8105c0b31c11fb69e2ec549b78b40d542246db4"},"schema_version":"1.0"},"canonical_sha256":"5b5797fad9d8dc317eadc5647d264186904b8b61dea66312eb962a523c996ba1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:52.046112Z","signature_b64":"EAlixXoEbmcoTIvRF9QgmSSLP5YdsPNy+Z8g8uj5J8w5YvI/cMbYhaQa/qNZSfTPmpvkDHuWNT/U/mkBXZ0bDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5797fad9d8dc317eadc5647d264186904b8b61dea66312eb962a523c996ba1","last_reissued_at":"2026-07-05T10:47:52.045621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:52.045621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.08641","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xE/MsdoDVESrMPAjclzYn9PQ/Ypa3mxoff1HNfjyB7sYbyiRyAhTDvZN0+ughTYmWrAPQD+P3qq25OPyFh6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:35:19.981769Z"},"content_sha256":"cac3e65b45d769c0a297fd9c70c9a1bd93edd7dfce1271c6b479f3098a3e3bd0","schema_version":"1.0","event_id":"sha256:cac3e65b45d769c0a297fd9c70c9a1bd93edd7dfce1271c6b479f3098a3e3bd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LNLZP6WZ3DODC7VNYVSH2JSBQ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Han Lin, Jaehong Yoon, Jaemin Cho, Jialu Li, Mohit Bansal, Shoubin Yu","submitted_at":"2025-04-11T15:41:43Z","abstract_excerpt":"Recent advancements in text-to-video (T2V) diffusion models have significantly enhanced the visual quality of the generated videos. However, even recent T2V models find it challenging to follow text descriptions accurately, especially when the prompt requires accurate control of spatial layouts or object trajectories. A recent line of research uses layout guidance for T2V models that require fine-tuning or iterative manipulation of the attention map during inference time. This significantly increases the memory requirement, making it difficult to adopt a large T2V model as a backbone. To addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08641","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/2504.08641/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e4Yg76LIFik2dIh2eO1TWgmUR4g/nGCKvhu6dhBBOq3/5ErA/LvvdHcwvFJdwk+c2AiOtNzfaSISNkHgsPuVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:35:19.982765Z"},"content_sha256":"27bc4ba7d48e0df7b0f7c3b63b37b11142f6f5afac01696f6eb3f9960a5823a3","schema_version":"1.0","event_id":"sha256:27bc4ba7d48e0df7b0f7c3b63b37b11142f6f5afac01696f6eb3f9960a5823a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LNLZP6WZ3DODC7VNYVSH2JSBQ2/bundle.json","state_url":"https://pith.science/pith/LNLZP6WZ3DODC7VNYVSH2JSBQ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LNLZP6WZ3DODC7VNYVSH2JSBQ2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:35:19Z","links":{"resolver":"https://pith.science/pith/LNLZP6WZ3DODC7VNYVSH2JSBQ2","bundle":"https://pith.science/pith/LNLZP6WZ3DODC7VNYVSH2JSBQ2/bundle.json","state":"https://pith.science/pith/LNLZP6WZ3DODC7VNYVSH2JSBQ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LNLZP6WZ3DODC7VNYVSH2JSBQ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LNLZP6WZ3DODC7VNYVSH2JSBQ2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ec14c3370ae41ea1263c0f94f8105c0b31c11fb69e2ec549b78b40d542246db4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T15:41:43Z","title_canon_sha256":"038528a8e1d7ed7122b115838b33287e00031d7632d1a07c06cc19e333b0540d"},"schema_version":"1.0","source":{"id":"2504.08641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08641","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08641v1","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08641","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"LNLZP6WZ3DOD","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"LNLZP6WZ3DODC7VN","created_at":"2026-07-05T10:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"LNLZP6WZ","created_at":"2026-07-05T10:47:52Z"}],"graph_snapshots":[{"event_id":"sha256:27bc4ba7d48e0df7b0f7c3b63b37b11142f6f5afac01696f6eb3f9960a5823a3","target":"graph","created_at":"2026-07-05T10:47:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.08641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in text-to-video (T2V) diffusion models have significantly enhanced the visual quality of the generated videos. However, even recent T2V models find it challenging to follow text descriptions accurately, especially when the prompt requires accurate control of spatial layouts or object trajectories. A recent line of research uses layout guidance for T2V models that require fine-tuning or iterative manipulation of the attention map during inference time. This significantly increases the memory requirement, making it difficult to adopt a large T2V model as a backbone. To addre","authors_text":"Han Lin, Jaehong Yoon, Jaemin Cho, Jialu Li, Mohit Bansal, Shoubin Yu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T15:41:43Z","title":"Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08641","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cac3e65b45d769c0a297fd9c70c9a1bd93edd7dfce1271c6b479f3098a3e3bd0","target":"record","created_at":"2026-07-05T10:47:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ec14c3370ae41ea1263c0f94f8105c0b31c11fb69e2ec549b78b40d542246db4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T15:41:43Z","title_canon_sha256":"038528a8e1d7ed7122b115838b33287e00031d7632d1a07c06cc19e333b0540d"},"schema_version":"1.0","source":{"id":"2504.08641","kind":"arxiv","version":1}},"canonical_sha256":"5b5797fad9d8dc317eadc5647d264186904b8b61dea66312eb962a523c996ba1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b5797fad9d8dc317eadc5647d264186904b8b61dea66312eb962a523c996ba1","first_computed_at":"2026-07-05T10:47:52.045621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:52.045621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EAlixXoEbmcoTIvRF9QgmSSLP5YdsPNy+Z8g8uj5J8w5YvI/cMbYhaQa/qNZSfTPmpvkDHuWNT/U/mkBXZ0bDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:52.046112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cac3e65b45d769c0a297fd9c70c9a1bd93edd7dfce1271c6b479f3098a3e3bd0","sha256:27bc4ba7d48e0df7b0f7c3b63b37b11142f6f5afac01696f6eb3f9960a5823a3"],"state_sha256":"984284adad3422927800a129bc0ea39ef8cd449617e95a83942357ded7a4073d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"21DZ5SmbLs1UmDRHGOBySjdaKnc2+e/6A9ByPcUfX9s8V/pU6yICL6LE67FCedWB1CNUP9mFdo127lU29lnuCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:35:19.989615Z","bundle_sha256":"5e80d325a9f6cbb3044476c71cd969955494656c297607bf301cac41c73364fd"}}