{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TYKR2AQOGP7Q6IO3UWC7YMPNQQ","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":"a9de7b3eea9049a7eca683f209edb9742f3ef3a9c7d0ffa56221f6a7227a94dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:59:58Z","title_canon_sha256":"480f285e7ea35a7db024ecc11ca40050ba98d844026127c07d0b4d3d1a9da925"},"schema_version":"1.0","source":{"id":"2403.12042","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12042","created_at":"2026-07-05T08:40:39Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12042v2","created_at":"2026-07-05T08:40:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12042","created_at":"2026-07-05T08:40:39Z"},{"alias_kind":"pith_short_12","alias_value":"TYKR2AQOGP7Q","created_at":"2026-07-05T08:40:39Z"},{"alias_kind":"pith_short_16","alias_value":"TYKR2AQOGP7Q6IO3","created_at":"2026-07-05T08:40:39Z"},{"alias_kind":"pith_short_8","alias_value":"TYKR2AQO","created_at":"2026-07-05T08:40:39Z"}],"graph_snapshots":[{"event_id":"sha256:dbfa44e881c7a17335542c140d5da153d70d210db8c4a0bded46485cb47fe195","target":"graph","created_at":"2026-07-05T08:40:39Z","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/2403.12042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding. Our hypothesis is validated through the classic referring video object segmentation (R-VOS) task. We introduce a novel framework, termed \"VD-IT\", tailored with dedicatedly designed components built upon a fixed pretrained T2V model. Specifi","authors_text":"Chunming Qiao, Dongdong Chen, Gang Hua, Junsong Yuan, Xuelu Feng, Zixin Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:59:58Z","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12042","kind":"arxiv","version":2},"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":"sha256:1ddcaabbaaa83ea1ddf93a76a32dc6e41a5a7581713e88ad57039146d2fe39b7","target":"record","created_at":"2026-07-05T08:40:39Z","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":"a9de7b3eea9049a7eca683f209edb9742f3ef3a9c7d0ffa56221f6a7227a94dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:59:58Z","title_canon_sha256":"480f285e7ea35a7db024ecc11ca40050ba98d844026127c07d0b4d3d1a9da925"},"schema_version":"1.0","source":{"id":"2403.12042","kind":"arxiv","version":2}},"canonical_sha256":"9e151d020e33ff0f21dba585fc31ed840158accfc21e457ae2cae286c5119890","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e151d020e33ff0f21dba585fc31ed840158accfc21e457ae2cae286c5119890","first_computed_at":"2026-07-05T08:40:39.656943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:39.656943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XnNR6nVmcQhlNtw+Um+wzBB70kRBVx9HSlp4J46DSXq2SCbEP/nDdjXnKtGvlFlOOpZXV4o2fd/tMb+et8kbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:39.657424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12042","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ddcaabbaaa83ea1ddf93a76a32dc6e41a5a7581713e88ad57039146d2fe39b7","sha256:dbfa44e881c7a17335542c140d5da153d70d210db8c4a0bded46485cb47fe195"],"state_sha256":"a39e035a72fb8227c4f93c2731134d9aaaeeab977232179d12efa672d7b889bd"}