{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y27RRRO4USDHW5FFDIYVXKKMZU","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":"4cb4d6c16ae4d4bb89d378cfb09df6fde05346d6a9545cc589d7796e0c26a7e0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T06:42:15Z","title_canon_sha256":"36c8f3a99d52f42bf2a371af83b6704cdaccd76d8b53ea72f1d69687f98c9f0a"},"schema_version":"1.0","source":{"id":"2605.20795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20795","created_at":"2026-05-21T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20795v1","created_at":"2026-05-21T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20795","created_at":"2026-05-21T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"Y27RRRO4USDH","created_at":"2026-05-21T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"Y27RRRO4USDHW5FF","created_at":"2026-05-21T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"Y27RRRO4","created_at":"2026-05-21T01:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:73290334446decb2e788480a760b59722274bb3d0ecc8d151d74ed7a426e330a","target":"graph","created_at":"2026-05-21T01:04:54Z","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/2605.20795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-based video editing. The prevailing assumption underlying this paradigm is that a connector module can seamlessly align the VLM's rich multi-modal reasoning with the original text embedding space of DiTs. However, we hypothesize that this alignment acts as a severe semantic bottleneck, degrading fine-grained structural variables. Verifying this is challenging, as end-to-end evaluations conflate alignment failures with generation errors, and natura","authors_text":"Chao Wen, Chengming Xu, Hangyu Lin, Jiangning Zhang, Jianxiong Gao, Xiaobin Hu, Yanwei Fu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T06:42:15Z","title":"What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20795","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":"sha256:03cb61f05432ad04bc3b713e04462967bdbd908b03e74253cd2d9e22419f4d97","target":"record","created_at":"2026-05-21T01:04:54Z","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":"4cb4d6c16ae4d4bb89d378cfb09df6fde05346d6a9545cc589d7796e0c26a7e0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T06:42:15Z","title_canon_sha256":"36c8f3a99d52f42bf2a371af83b6704cdaccd76d8b53ea72f1d69687f98c9f0a"},"schema_version":"1.0","source":{"id":"2605.20795","kind":"arxiv","version":1}},"canonical_sha256":"c6bf18c5dca4867b74a51a315ba94ccd1ca608ee5e8cfefbef669d42f175c0fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6bf18c5dca4867b74a51a315ba94ccd1ca608ee5e8cfefbef669d42f175c0fc","first_computed_at":"2026-05-21T01:04:54.892219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:54.892219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GvP7ciLAv4dVYFTGZ34AwtXynXzMw7LDkfvzY4qKnsZWjrCluxamRoOXKxwCRiYhhRaNy5+7TJ4wRjXYjh5/AQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:54.893196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03cb61f05432ad04bc3b713e04462967bdbd908b03e74253cd2d9e22419f4d97","sha256:73290334446decb2e788480a760b59722274bb3d0ecc8d151d74ed7a426e330a"],"state_sha256":"55c0e999cd97f25edca9b593352edc9ce4fc5958dfdb17adb1aa90909da6b681"}