{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TDIPEKTJBJANXF4M6NQCNE6VBV","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":"95d20e0513a2960e7dea1ee893f6121e0b12d0d75a403ed4480ef0f7be56439c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T02:55:10Z","title_canon_sha256":"cc4fde3f9c24c2206e9c05fe22f8137bafc17f9b6068236856863e16273333ae"},"schema_version":"1.0","source":{"id":"2608.03046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03046","created_at":"2026-08-05T00:44:59Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03046v1","created_at":"2026-08-05T00:44:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03046","created_at":"2026-08-05T00:44:59Z"},{"alias_kind":"pith_short_12","alias_value":"TDIPEKTJBJAN","created_at":"2026-08-05T00:44:59Z"},{"alias_kind":"pith_short_16","alias_value":"TDIPEKTJBJANXF4M","created_at":"2026-08-05T00:44:59Z"},{"alias_kind":"pith_short_8","alias_value":"TDIPEKTJ","created_at":"2026-08-05T00:44:59Z"}],"graph_snapshots":[{"event_id":"sha256:f55eb95656d1d95333f40135ee1c64d1897e236ad88ef7d0d489b81a0043580e","target":"graph","created_at":"2026-08-05T00:44:59Z","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/2608.03046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video (T2V) diffusion transformers (DiTs) are trained with detailed video captions, whereas inference often relies on user prompts rewritten by a prompt enhancer (PE). Prior work has improved generation by optimizing the PE, the DiT, or both; some methods have also sought to narrow the training-inference mismatch through shared schemas. Yet even within a shared schema, inference-time PE outputs and DiT training captions may still differ in detail selection, information organization, descriptive granularity, and phrasing. We refer to this residual mismatch as the PE-Caption gap and intr","authors_text":"Jingyun Hua, Yizhuo Jia, Yuanxing Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T02:55:10Z","title":"CAPE-T2V: Captioner-Anchored Prompt Enhancement toward Two-Sided Conditioning Alignment in Text-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03046","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:ee315dae4277bc625787c3687068978820487d28c9d72546612a216e28fd935e","target":"record","created_at":"2026-08-05T00:44:59Z","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":"95d20e0513a2960e7dea1ee893f6121e0b12d0d75a403ed4480ef0f7be56439c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T02:55:10Z","title_canon_sha256":"cc4fde3f9c24c2206e9c05fe22f8137bafc17f9b6068236856863e16273333ae"},"schema_version":"1.0","source":{"id":"2608.03046","kind":"arxiv","version":1}},"canonical_sha256":"98d0f22a690a40db978cf3602693d50d4fa6a7fee72d18a4ef365e250ec42d90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98d0f22a690a40db978cf3602693d50d4fa6a7fee72d18a4ef365e250ec42d90","first_computed_at":"2026-08-05T00:44:59.718595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:44:59.718595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qTCsd/dKa0KPVhghcj4/yHC2gOBH3oBuSkyMXmMudpbQpuB/iobqD+uNoXq7K5uccnI0qUg8smZywP1gA5P2AA==","signature_status":"signed_v1","signed_at":"2026-08-05T00:44:59.721080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee315dae4277bc625787c3687068978820487d28c9d72546612a216e28fd935e","sha256:f55eb95656d1d95333f40135ee1c64d1897e236ad88ef7d0d489b81a0043580e"],"state_sha256":"ee292cb286db99c4a65dc213e382f5077d34cf2c19ee5f8c262a3ba76a090231"}