{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SCAP67M6Q6LEEFMKRNA5CEDEQB","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":"88b9ce7a927be2f7c0e2ffa3740a8461924777ba2e619babac98f6d532c4a123","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:57Z","title_canon_sha256":"b5c11290b9550d64a547a0c2ee26775ebebfb4e11d6266f3539d61cfa3eed453"},"schema_version":"1.0","source":{"id":"2607.02551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02551","created_at":"2026-07-07T00:16:00Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02551v1","created_at":"2026-07-07T00:16:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02551","created_at":"2026-07-07T00:16:00Z"},{"alias_kind":"pith_short_12","alias_value":"SCAP67M6Q6LE","created_at":"2026-07-07T00:16:00Z"},{"alias_kind":"pith_short_16","alias_value":"SCAP67M6Q6LEEFMK","created_at":"2026-07-07T00:16:00Z"},{"alias_kind":"pith_short_8","alias_value":"SCAP67M6","created_at":"2026-07-07T00:16:00Z"}],"graph_snapshots":[{"event_id":"sha256:c19cb3f44ebbee779d163282f6523cd791eb425ff44ab74b667f54c434d51f90","target":"graph","created_at":"2026-07-07T00:16:00Z","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/2607.02551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video multimodal large language models have made strong progress on open-ended video understanding, but they still lack precise local spatiotemporal perception. When two videos share almost the same global semantics and differ only in a short time span or a small region, current models often fail to find the change and provide reliable evidence. We propose DELTAVID, a verifiable proxy-task framework that enhances fine-grained spatiotemporal perception with cross-video differences. The key idea is to turn cross-video spot-the-difference into a trainable perception signal, where a model identifi","authors_text":"Bin Wen, Fan Yang, Han Li, Shuo Yang, Tingting Gao, Yancheng Long, Yankai Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:57Z","title":"DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02551","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":"sha256:3bb2e5cab440d304f50d61f347270d179be89f2697fa9622e7532c8b95755fc0","target":"record","created_at":"2026-07-07T00:16:00Z","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":"88b9ce7a927be2f7c0e2ffa3740a8461924777ba2e619babac98f6d532c4a123","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:57Z","title_canon_sha256":"b5c11290b9550d64a547a0c2ee26775ebebfb4e11d6266f3539d61cfa3eed453"},"schema_version":"1.0","source":{"id":"2607.02551","kind":"arxiv","version":1}},"canonical_sha256":"9080ff7d9e879642158a8b41d11064804f75e3abba561b5d5ccfbb51f28dce3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9080ff7d9e879642158a8b41d11064804f75e3abba561b5d5ccfbb51f28dce3f","first_computed_at":"2026-07-07T00:16:00.263990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T00:16:00.263990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3KGKyswlLzClbd6ydZXzstcybQCkZ9JaZxRsYuK/C0XyjA4WOYQaSY3IqodwiwFuhn/R7Ja3bcln/svwc03aBA==","signature_status":"signed_v1","signed_at":"2026-07-07T00:16:00.264757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bb2e5cab440d304f50d61f347270d179be89f2697fa9622e7532c8b95755fc0","sha256:c19cb3f44ebbee779d163282f6523cd791eb425ff44ab74b667f54c434d51f90"],"state_sha256":"74513f1785deef9168c69bc989da52f44dd6632c07974cf16423ff67715f0f0d"}