{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y33XWNX2LJFW4LSMG7OTG3FHD5","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":"b7601d8d807b46d151c6a990b2f23cd216b819af5c38357d4b16454091a61469","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T18:37:08Z","title_canon_sha256":"bb9077e55c7803814a2185b06e8d901759f63316d9dd92c8fd2708904b779907"},"schema_version":"1.0","source":{"id":"2501.07554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07554","created_at":"2026-07-05T10:00:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07554v1","created_at":"2026-07-05T10:00:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07554","created_at":"2026-07-05T10:00:30Z"},{"alias_kind":"pith_short_12","alias_value":"Y33XWNX2LJFW","created_at":"2026-07-05T10:00:30Z"},{"alias_kind":"pith_short_16","alias_value":"Y33XWNX2LJFW4LSM","created_at":"2026-07-05T10:00:30Z"},{"alias_kind":"pith_short_8","alias_value":"Y33XWNX2","created_at":"2026-07-05T10:00:30Z"}],"graph_snapshots":[{"event_id":"sha256:26de0ac2cb6cf61441cfd66f9c58c7357bf8f9db4a13bce1dd06dd730068697c","target":"graph","created_at":"2026-07-05T10:00:30Z","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/2501.07554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and hierarchical dependencies, while image scores fail to assess temporal consistency. We present SST-EM (Semantic, Spatial, and Temporal Evaluation Metric), a novel evaluation framework that leverages modern Vision-Language Models (VLMs), Object Detection, and Temporal Consistency checks. SST-EM comprises four components: (1) semantic extraction from frames using a ","authors_text":"Bharat Chanderprakash Kathuria, Jialu Li, Varun Biyyala, Youshan Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T18:37:08Z","title":"SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07554","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":"sha256:04138b77ea0cd2776ec4be25bd88687b05ac7a8b55d7d594f1b6fb8a6357eed9","target":"record","created_at":"2026-07-05T10:00:30Z","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":"b7601d8d807b46d151c6a990b2f23cd216b819af5c38357d4b16454091a61469","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T18:37:08Z","title_canon_sha256":"bb9077e55c7803814a2185b06e8d901759f63316d9dd92c8fd2708904b779907"},"schema_version":"1.0","source":{"id":"2501.07554","kind":"arxiv","version":1}},"canonical_sha256":"c6f77b36fa5a4b6e2e4c37dd336ca71f7bca5f23f507a82dbc5f4d666af61061","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6f77b36fa5a4b6e2e4c37dd336ca71f7bca5f23f507a82dbc5f4d666af61061","first_computed_at":"2026-07-05T10:00:30.092383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:30.092383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0cNwpomxvEKTzva3+zLBEj7bYJlGK1beIUJAEQ8FlTi+lcKVdk82gpCiKVHdn12bZJPUKcqSlOgfeUnXO1p4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:30.092926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04138b77ea0cd2776ec4be25bd88687b05ac7a8b55d7d594f1b6fb8a6357eed9","sha256:26de0ac2cb6cf61441cfd66f9c58c7357bf8f9db4a13bce1dd06dd730068697c"],"state_sha256":"c4e0a6417985adde8e31ae6e1a3011688fda89280c3e788bc4014298849101b0"}