{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6CZ6GZAIZYMEXSCCP245OCOF3S","short_pith_number":"pith:6CZ6GZAI","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"},"canonical_sha256":"f0b3e36408ce184bc8427eb9d709c5dc887efc9211b8c41dbe699c0a3947e77a","source":{"kind":"arxiv","id":"2607.18789","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18789","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18789v1","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18789","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"6CZ6GZAIZYME","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"pith_short_16","alias_value":"6CZ6GZAIZYMEXSCC","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"pith_short_8","alias_value":"6CZ6GZAI","created_at":"2026-07-22T01:23:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6CZ6GZAIZYMEXSCCP245OCOF3S","target":"record","payload":{"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"},"canonical_sha256":"f0b3e36408ce184bc8427eb9d709c5dc887efc9211b8c41dbe699c0a3947e77a","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"},"source_kind":"arxiv","source_id":"2607.18789","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-22T01:23:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdr+bc3PQ+5WjzrBS7iWOPeFZ4jXh4tUIzEeXZdGDRMfmiqXtr4HOGvZ1AiWMG4seIJcp5ct7y6rJ+dxagMpCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:47:01.167927Z"},"content_sha256":"a56d2c7e196055c2f21db1d92a8b92e0606772802fe64b9a9121d21833a87cd9","schema_version":"1.0","event_id":"sha256:a56d2c7e196055c2f21db1d92a8b92e0606772802fe64b9a9121d21833a87cd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6CZ6GZAIZYMEXSCCP245OCOF3S","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-22T01:23:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7N01nxkYIBw87HxsjVQvC8Gv7F7FnHRYHR03jPt/Imhi6WZ/+E40h58+ESszxc6DPCQ29YPWMmZWMeZPq5eUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:47:01.168732Z"},"content_sha256":"2466190b5ab6b7a73ff4e8541328dadb923335a89015a7138e0b335a7f5edcc9","schema_version":"1.0","event_id":"sha256:2466190b5ab6b7a73ff4e8541328dadb923335a89015a7138e0b335a7f5edcc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/bundle.json","state_url":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T02:47:01Z","links":{"resolver":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S","bundle":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/bundle.json","state":"https://pith.science/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CZ6GZAIZYMEXSCCP245OCOF3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6CZ6GZAIZYMEXSCCP245OCOF3S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eafb286b9335eb0babd97df5ac4f176c1c71956b6c378eeb7914941c8f7241e9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T07:07:19Z","title_canon_sha256":"a2654397cb531d4a3b6a26e139016dde4a2a93731009941c281e89cd3c4c3e2f"},"schema_version":"1.0","source":{"id":"2607.18789","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18789","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18789v1","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18789","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"6CZ6GZAIZYME","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"pith_short_16","alias_value":"6CZ6GZAIZYMEXSCC","created_at":"2026-07-22T01:23:11Z"},{"alias_kind":"pith_short_8","alias_value":"6CZ6GZAI","created_at":"2026-07-22T01:23:11Z"}],"graph_snapshots":[{"event_id":"sha256:2466190b5ab6b7a73ff4e8541328dadb923335a89015a7138e0b335a7f5edcc9","target":"graph","created_at":"2026-07-22T01:23:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.18789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Amber Yijia Zheng, Lu Liu, Raymond A. Yeh, Xi Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T07:07:19Z","title":"Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18789","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a56d2c7e196055c2f21db1d92a8b92e0606772802fe64b9a9121d21833a87cd9","target":"record","created_at":"2026-07-22T01:23:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eafb286b9335eb0babd97df5ac4f176c1c71956b6c378eeb7914941c8f7241e9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T07:07:19Z","title_canon_sha256":"a2654397cb531d4a3b6a26e139016dde4a2a93731009941c281e89cd3c4c3e2f"},"schema_version":"1.0","source":{"id":"2607.18789","kind":"arxiv","version":1}},"canonical_sha256":"f0b3e36408ce184bc8427eb9d709c5dc887efc9211b8c41dbe699c0a3947e77a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0b3e36408ce184bc8427eb9d709c5dc887efc9211b8c41dbe699c0a3947e77a","first_computed_at":"2026-07-22T01:23:11.908197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:23:11.908197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tJRAl/xSaVWZkZ/rcuEnTysHNrXSLbgxv0T+eftiXhRDN7K8F/XWmg0o9o+BHgPa/IktTfO3nQs5nV4DlXWgDg==","signature_status":"signed_v1","signed_at":"2026-07-22T01:23:11.909048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18789","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a56d2c7e196055c2f21db1d92a8b92e0606772802fe64b9a9121d21833a87cd9","sha256:2466190b5ab6b7a73ff4e8541328dadb923335a89015a7138e0b335a7f5edcc9"],"state_sha256":"6484bbf94114c3fe0e39bc90a7586c95df0e47701ffea17dcca1f5b15bb579bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GIreY9DzGbQYhO6FA7M/lsSC4QC/p4I6CdgOY8xUg2xX/94Nlgt9S8dBSvdgWnXeXahUL9etBfqZ1fFSK7yDBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:47:01.173408Z","bundle_sha256":"8a90390f07f233e87d2990cd44b0313894a0d4c0df29f4db368c1458ae6408d0"}}