{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CMSGUGYVB7ZEND6ME5HAXPRNC2","short_pith_number":"pith:CMSGUGYV","schema_version":"1.0","canonical_sha256":"13246a1b150ff2468fcc274e0bbe2d168875d02febe072629e1dc725eddbf2ab","source":{"kind":"arxiv","id":"2411.04989","version":3},"attestation_state":"computed","paper":{"title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David B. Lindell, Igor Gilitschenski, Koichi Namekata, Sherwin Bahmani, Yash Kant, Ziyi Wu","submitted_at":"2024-11-07T18:56:11Z","abstract_excerpt":"Methods for image-to-video generation have achieved impressive, photo-realistic quality. However, adjusting specific elements in generated videos, such as object motion or camera movement, is often a tedious process of trial and error, e.g., involving re-generating videos with different random seeds. Recent techniques address this issue by fine-tuning a pre-trained model to follow conditioning signals, such as bounding boxes or point trajectories. Yet, this fine-tuning procedure can be computationally expensive, and it requires datasets with annotated object motion, which can be difficult to p"},"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":"2411.04989","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:56:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4760ed54cea720ccaa3bc950c8d8672dd004807079c2e19abb4f63398529a239","abstract_canon_sha256":"9a8f69ccaf4e4f2de4c6e9d5ee8deb4b659c941e996aaf88b18965299b5a6357"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:30.767686Z","signature_b64":"5mbOQwYOarjt/kJ7+J3uobViu4ZBAzu91eXC269YO3Mwxyw8fil8d+ee8DYgQ7kGCexwwrdGHAphBQekHjgqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13246a1b150ff2468fcc274e0bbe2d168875d02febe072629e1dc725eddbf2ab","last_reissued_at":"2026-07-05T10:19:30.767181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:30.767181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David B. Lindell, Igor Gilitschenski, Koichi Namekata, Sherwin Bahmani, Yash Kant, Ziyi Wu","submitted_at":"2024-11-07T18:56:11Z","abstract_excerpt":"Methods for image-to-video generation have achieved impressive, photo-realistic quality. However, adjusting specific elements in generated videos, such as object motion or camera movement, is often a tedious process of trial and error, e.g., involving re-generating videos with different random seeds. Recent techniques address this issue by fine-tuning a pre-trained model to follow conditioning signals, such as bounding boxes or point trajectories. Yet, this fine-tuning procedure can be computationally expensive, and it requires datasets with annotated object motion, which can be difficult to p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04989","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/2411.04989/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":"2411.04989","created_at":"2026-07-05T10:19:30.767238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04989v3","created_at":"2026-07-05T10:19:30.767238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04989","created_at":"2026-07-05T10:19:30.767238+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMSGUGYVB7ZE","created_at":"2026-07-05T10:19:30.767238+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMSGUGYVB7ZEND6M","created_at":"2026-07-05T10:19:30.767238+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMSGUGYV","created_at":"2026-07-05T10:19:30.767238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08770","citing_title":"LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01869","citing_title":"QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09187","citing_title":"CP4D: Compositional Physics-aware 4D Scene Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31529","citing_title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06280","citing_title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31529","citing_title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16420","citing_title":"Video Reconstruction using Diffusion-based Image-to-Video Generation with Trajectory Guidance","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03305","citing_title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06280","citing_title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06280","citing_title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06280","citing_title":"Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2","json":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2.json","graph_json":"https://pith.science/api/pith-number/CMSGUGYVB7ZEND6ME5HAXPRNC2/graph.json","events_json":"https://pith.science/api/pith-number/CMSGUGYVB7ZEND6ME5HAXPRNC2/events.json","paper":"https://pith.science/paper/CMSGUGYV"},"agent_actions":{"view_html":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2","download_json":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2.json","view_paper":"https://pith.science/paper/CMSGUGYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04989&json=true","fetch_graph":"https://pith.science/api/pith-number/CMSGUGYVB7ZEND6ME5HAXPRNC2/graph.json","fetch_events":"https://pith.science/api/pith-number/CMSGUGYVB7ZEND6ME5HAXPRNC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2/action/storage_attestation","attest_author":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2/action/author_attestation","sign_citation":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2/action/citation_signature","submit_replication":"https://pith.science/pith/CMSGUGYVB7ZEND6ME5HAXPRNC2/action/replication_record"}},"created_at":"2026-07-05T10:19:30.767238+00:00","updated_at":"2026-07-05T10:19:30.767238+00:00"}