{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6CZ6GZAIZYMEXSCCP245OCOF3S","short_pith_number":"pith:6CZ6GZAI","schema_version":"1.0","canonical_sha256":"f0b3e36408ce184bc8427eb9d709c5dc887efc9211b8c41dbe699c0a3947e77a","source":{"kind":"arxiv","id":"2607.18789","version":1},"attestation_state":"computed","paper":{"title":"Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amber Yijia Zheng, Lu Liu, Raymond A. Yeh, Xi Yin","submitted_at":"2026-07-21T07:07:19Z","abstract_excerpt":"Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and compute. Unlike model architecture, training data is often underexplored. Real-world data curation is complex and non-trivial, involving clip selection from raw videos and captioning to create video-text pairs for learning text-to-video mappings. We study how data distribution and caption quality impact text-to-video models. To enable controlled experiments, we introduce Moving Alphabet, a procedural testbed that renders letters with varying fonts, colors, sizes, and positions,"},"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":"2607.18789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T07:07:19Z","cross_cats_sorted":[],"title_canon_sha256":"a2654397cb531d4a3b6a26e139016dde4a2a93731009941c281e89cd3c4c3e2f","abstract_canon_sha256":"eafb286b9335eb0babd97df5ac4f176c1c71956b6c378eeb7914941c8f7241e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:11.909048Z","signature_b64":"tJRAl/xSaVWZkZ/rcuEnTysHNrXSLbgxv0T+eftiXhRDN7K8F/XWmg0o9o+BHgPa/IktTfO3nQs5nV4DlXWgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0b3e36408ce184bc8427eb9d709c5dc887efc9211b8c41dbe699c0a3947e77a","last_reissued_at":"2026-07-22T01:23:11.908197Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:11.908197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amber Yijia Zheng, Lu Liu, Raymond A. Yeh, Xi Yin","submitted_at":"2026-07-21T07:07:19Z","abstract_excerpt":"Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and compute. Unlike model architecture, training data is often underexplored. Real-world data curation is complex and non-trivial, involving clip selection from raw videos and captioning to create video-text pairs for learning text-to-video mappings. We study how data distribution and caption quality impact text-to-video models. To enable controlled experiments, we introduce Moving Alphabet, a procedural testbed that renders letters with varying fonts, colors, sizes, and positions,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18789","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/2607.18789/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":"2607.18789","created_at":"2026-07-22T01:23:11.908643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18789v1","created_at":"2026-07-22T01:23:11.908643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18789","created_at":"2026-07-22T01:23:11.908643+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CZ6GZAIZYME","created_at":"2026-07-22T01:23:11.908643+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CZ6GZAIZYMEXSCC","created_at":"2026-07-22T01:23:11.908643+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CZ6GZAI","created_at":"2026-07-22T01:23:11.908643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S","json":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S.json","graph_json":"https://pith.science/api/pith-number/6CZ6GZAIZYMEXSCCP245OCOF3S/graph.json","events_json":"https://pith.science/api/pith-number/6CZ6GZAIZYMEXSCCP245OCOF3S/events.json","paper":"https://pith.science/paper/6CZ6GZAI"},"agent_actions":{"view_html":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S","download_json":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S.json","view_paper":"https://pith.science/paper/6CZ6GZAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18789&json=true","fetch_graph":"https://pith.science/api/pith-number/6CZ6GZAIZYMEXSCCP245OCOF3S/graph.json","fetch_events":"https://pith.science/api/pith-number/6CZ6GZAIZYMEXSCCP245OCOF3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/action/storage_attestation","attest_author":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/action/author_attestation","sign_citation":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/action/citation_signature","submit_replication":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/action/replication_record"}},"created_at":"2026-07-22T01:23:11.908643+00:00","updated_at":"2026-07-22T01:23:11.908643+00:00"}