{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MCUM2ME7TE3LO4IKOPKV4I57UT","short_pith_number":"pith:MCUM2ME7","schema_version":"1.0","canonical_sha256":"60a8cd309f9936b7710a73d55e23bfa4f09c0e7ec0741f059a504f19de66f695","source":{"kind":"arxiv","id":"2401.18085","version":1},"attestation_state":"computed","paper":{"title":"Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Daniel Geng","submitted_at":"2024-01-31T18:59:59Z","abstract_excerpt":"Diffusion models are capable of generating impressive images conditioned on text descriptions, and extensions of these models allow users to edit images at a relatively coarse scale. However, the ability to precisely edit the layout, position, pose, and shape of objects in images with diffusion models is still difficult. To this end, we propose motion guidance, a zero-shot technique that allows a user to specify dense, complex motion fields that indicate where each pixel in an image should move. Motion guidance works by steering the diffusion sampling process with the gradients through an off-"},"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":"2401.18085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"2fd27ed292580a95a944882889086ad98e0232dcc316e9c0a2e3bc1ddf77f43e","abstract_canon_sha256":"d753a659597bb96153d634e524352ae134a2cc647b1a73e685bee1dd3132a3c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:46.782086Z","signature_b64":"ouogZKzii25UoF5cZiCH3aD9xgH0WOUUPh4/pLhFi3I4A3DNKbv3FSQenEi+5m83GXVA+dKrnomxfwI/dR62Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60a8cd309f9936b7710a73d55e23bfa4f09c0e7ec0741f059a504f19de66f695","last_reissued_at":"2026-07-05T07:39:46.781668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:46.781668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Daniel Geng","submitted_at":"2024-01-31T18:59:59Z","abstract_excerpt":"Diffusion models are capable of generating impressive images conditioned on text descriptions, and extensions of these models allow users to edit images at a relatively coarse scale. However, the ability to precisely edit the layout, position, pose, and shape of objects in images with diffusion models is still difficult. To this end, we propose motion guidance, a zero-shot technique that allows a user to specify dense, complex motion fields that indicate where each pixel in an image should move. Motion guidance works by steering the diffusion sampling process with the gradients through an off-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.18085","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/2401.18085/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":"2401.18085","created_at":"2026-07-05T07:39:46.781723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.18085v1","created_at":"2026-07-05T07:39:46.781723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.18085","created_at":"2026-07-05T07:39:46.781723+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCUM2ME7TE3L","created_at":"2026-07-05T07:39:46.781723+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCUM2ME7TE3LO4IK","created_at":"2026-07-05T07:39:46.781723+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCUM2ME7","created_at":"2026-07-05T07:39:46.781723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.25845","citing_title":"Training-Free Reward-Guided Image Editing via Trajectory Optimal Control","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT","json":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT.json","graph_json":"https://pith.science/api/pith-number/MCUM2ME7TE3LO4IKOPKV4I57UT/graph.json","events_json":"https://pith.science/api/pith-number/MCUM2ME7TE3LO4IKOPKV4I57UT/events.json","paper":"https://pith.science/paper/MCUM2ME7"},"agent_actions":{"view_html":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT","download_json":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT.json","view_paper":"https://pith.science/paper/MCUM2ME7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.18085&json=true","fetch_graph":"https://pith.science/api/pith-number/MCUM2ME7TE3LO4IKOPKV4I57UT/graph.json","fetch_events":"https://pith.science/api/pith-number/MCUM2ME7TE3LO4IKOPKV4I57UT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT/action/storage_attestation","attest_author":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT/action/author_attestation","sign_citation":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT/action/citation_signature","submit_replication":"https://pith.science/pith/MCUM2ME7TE3LO4IKOPKV4I57UT/action/replication_record"}},"created_at":"2026-07-05T07:39:46.781723+00:00","updated_at":"2026-07-05T07:39:46.781723+00:00"}