{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EQOKFT7EL2AH42QGTMX56K76XT","short_pith_number":"pith:EQOKFT7E","schema_version":"1.0","canonical_sha256":"241ca2cfe45e807e6a069b2fdf2bfebcf0babc71f4808c3ca92de2ac92d1c555","source":{"kind":"arxiv","id":"2412.14158","version":2},"attestation_state":"computed","paper":{"title":"AKiRa: Augmentation Kit on Rays for optical video generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Marc Christie, Robin Courant, Vicky Kalogeiton, Xi Wang","submitted_at":"2024-12-18T18:53:22Z","abstract_excerpt":"Recent advances in text-conditioned video diffusion have greatly improved video quality. However, these methods offer limited or sometimes no control to users on camera aspects, including dynamic camera motion, zoom, distorted lens and focus shifts. These motion and optical aspects are crucial for adding controllability and cinematic elements to generation frameworks, ultimately resulting in visual content that draws focus, enhances mood, and guides emotions according to filmmakers' controls. In this paper, we aim to close the gap between controllable video generation and camera optics. To ach"},"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":"2412.14158","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:53:22Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"d8eac1a06e3aecba0b3016f99574ba95eac77ac6a375966d304d967c7a8a732b","abstract_canon_sha256":"1cf16ab5b729034de7aa3ebfbb5744047db5278f8b8960a5b341e71ec35d5d12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:15.172546Z","signature_b64":"3xTkMudg1gjdKv0LD5VZ3vDYhgg4770O0Vpet6BGYNKn5ImZ55XJzQ1wg3qL+ofNCOaVlsLDhxJut0Cnhx5VCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"241ca2cfe45e807e6a069b2fdf2bfebcf0babc71f4808c3ca92de2ac92d1c555","last_reissued_at":"2026-07-05T09:55:15.172120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:15.172120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AKiRa: Augmentation Kit on Rays for optical video generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Marc Christie, Robin Courant, Vicky Kalogeiton, Xi Wang","submitted_at":"2024-12-18T18:53:22Z","abstract_excerpt":"Recent advances in text-conditioned video diffusion have greatly improved video quality. However, these methods offer limited or sometimes no control to users on camera aspects, including dynamic camera motion, zoom, distorted lens and focus shifts. These motion and optical aspects are crucial for adding controllability and cinematic elements to generation frameworks, ultimately resulting in visual content that draws focus, enhances mood, and guides emotions according to filmmakers' controls. In this paper, we aim to close the gap between controllable video generation and camera optics. To ach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14158","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/2412.14158/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":"2412.14158","created_at":"2026-07-05T09:55:15.172175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14158v2","created_at":"2026-07-05T09:55:15.172175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14158","created_at":"2026-07-05T09:55:15.172175+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQOKFT7EL2AH","created_at":"2026-07-05T09:55:15.172175+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQOKFT7EL2AH42QG","created_at":"2026-07-05T09:55:15.172175+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQOKFT7E","created_at":"2026-07-05T09:55:15.172175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02467","citing_title":"VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT","json":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT.json","graph_json":"https://pith.science/api/pith-number/EQOKFT7EL2AH42QGTMX56K76XT/graph.json","events_json":"https://pith.science/api/pith-number/EQOKFT7EL2AH42QGTMX56K76XT/events.json","paper":"https://pith.science/paper/EQOKFT7E"},"agent_actions":{"view_html":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT","download_json":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT.json","view_paper":"https://pith.science/paper/EQOKFT7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14158&json=true","fetch_graph":"https://pith.science/api/pith-number/EQOKFT7EL2AH42QGTMX56K76XT/graph.json","fetch_events":"https://pith.science/api/pith-number/EQOKFT7EL2AH42QGTMX56K76XT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT/action/storage_attestation","attest_author":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT/action/author_attestation","sign_citation":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT/action/citation_signature","submit_replication":"https://pith.science/pith/EQOKFT7EL2AH42QGTMX56K76XT/action/replication_record"}},"created_at":"2026-07-05T09:55:15.172175+00:00","updated_at":"2026-07-05T09:55:15.172175+00:00"}