{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:COP73ULR2JNESBAJE6CY3U7GCB","short_pith_number":"pith:COP73ULR","schema_version":"1.0","canonical_sha256":"139ffdd171d25a49040927858dd3e6106ca34babdf833b9514d133b41f8903ba","source":{"kind":"arxiv","id":"2501.03059","version":1},"attestation_state":"computed","paper":{"title":"Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Amit Zohar, Guy Yariv, Sagie Benaim, Shelly Sheynin, Yaniv Taigman, Yossi Adi, Yuval Kirstain","submitted_at":"2025-01-06T14:49:26Z","abstract_excerpt":"We consider the task of Image-to-Video (I2V) generation, which involves transforming static images into realistic video sequences based on a textual description. While recent advancements produce photorealistic outputs, they frequently struggle to create videos with accurate and consistent object motion, especially in multi-object scenarios. To address these limitations, we propose a two-stage compositional framework that decomposes I2V generation into: (i) An explicit intermediate representation generation stage, followed by (ii) A video generation stage that is conditioned on this representa"},"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":"2501.03059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T14:49:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d29a3a1da5b986bbcd1f3830803533a4f8a38b2af808c8c980f378dccd89d21d","abstract_canon_sha256":"716b95a5a419dd47cf3b5931e19f2d4b08296e236acb1867ca76e88ea5cfbe27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:30.074865Z","signature_b64":"M5FM3/7N5J5Soj41iXtM4WVs7cZ+EOPcr+ESlLuHQemRXGwx9hxdZeUKpvwrY7ur8m4KXuLH9X/IklfO09tjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"139ffdd171d25a49040927858dd3e6106ca34babdf833b9514d133b41f8903ba","last_reissued_at":"2026-07-05T09:57:30.074403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:30.074403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Amit Zohar, Guy Yariv, Sagie Benaim, Shelly Sheynin, Yaniv Taigman, Yossi Adi, Yuval Kirstain","submitted_at":"2025-01-06T14:49:26Z","abstract_excerpt":"We consider the task of Image-to-Video (I2V) generation, which involves transforming static images into realistic video sequences based on a textual description. While recent advancements produce photorealistic outputs, they frequently struggle to create videos with accurate and consistent object motion, especially in multi-object scenarios. To address these limitations, we propose a two-stage compositional framework that decomposes I2V generation into: (i) An explicit intermediate representation generation stage, followed by (ii) A video generation stage that is conditioned on this representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03059","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/2501.03059/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":"2501.03059","created_at":"2026-07-05T09:57:30.074464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03059v1","created_at":"2026-07-05T09:57:30.074464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03059","created_at":"2026-07-05T09:57:30.074464+00:00"},{"alias_kind":"pith_short_12","alias_value":"COP73ULR2JNE","created_at":"2026-07-05T09:57:30.074464+00:00"},{"alias_kind":"pith_short_16","alias_value":"COP73ULR2JNESBAJ","created_at":"2026-07-05T09:57:30.074464+00:00"},{"alias_kind":"pith_short_8","alias_value":"COP73ULR","created_at":"2026-07-05T09:57:30.074464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":227,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB","json":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB.json","graph_json":"https://pith.science/api/pith-number/COP73ULR2JNESBAJE6CY3U7GCB/graph.json","events_json":"https://pith.science/api/pith-number/COP73ULR2JNESBAJE6CY3U7GCB/events.json","paper":"https://pith.science/paper/COP73ULR"},"agent_actions":{"view_html":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB","download_json":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB.json","view_paper":"https://pith.science/paper/COP73ULR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03059&json=true","fetch_graph":"https://pith.science/api/pith-number/COP73ULR2JNESBAJE6CY3U7GCB/graph.json","fetch_events":"https://pith.science/api/pith-number/COP73ULR2JNESBAJE6CY3U7GCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB/action/storage_attestation","attest_author":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB/action/author_attestation","sign_citation":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB/action/citation_signature","submit_replication":"https://pith.science/pith/COP73ULR2JNESBAJE6CY3U7GCB/action/replication_record"}},"created_at":"2026-07-05T09:57:30.074464+00:00","updated_at":"2026-07-05T09:57:30.074464+00:00"}