{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SCAP67M6Q6LEEFMKRNA5CEDEQB","short_pith_number":"pith:SCAP67M6","schema_version":"1.0","canonical_sha256":"9080ff7d9e879642158a8b41d11064804f75e3abba561b5d5ccfbb51f28dce3f","source":{"kind":"arxiv","id":"2607.02551","version":1},"attestation_state":"computed","paper":{"title":"DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Wen, Fan Yang, Han Li, Shuo Yang, Tingting Gao, Yancheng Long, Yankai Yang","submitted_at":"2026-06-26T16:05:57Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.02551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:05:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5c11290b9550d64a547a0c2ee26775ebebfb4e11d6266f3539d61cfa3eed453","abstract_canon_sha256":"88b9ce7a927be2f7c0e2ffa3740a8461924777ba2e619babac98f6d532c4a123"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:00.264757Z","signature_b64":"3KGKyswlLzClbd6ydZXzstcybQCkZ9JaZxRsYuK/C0XyjA4WOYQaSY3IqodwiwFuhn/R7Ja3bcln/svwc03aBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9080ff7d9e879642158a8b41d11064804f75e3abba561b5d5ccfbb51f28dce3f","last_reissued_at":"2026-07-07T00:16:00.263990Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:00.263990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Wen, Fan Yang, Han Li, Shuo Yang, Tingting Gao, Yancheng Long, Yankai Yang","submitted_at":"2026-06-26T16:05:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02551","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.02551/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.02551","created_at":"2026-07-07T00:16:00.264091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02551v1","created_at":"2026-07-07T00:16:00.264091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02551","created_at":"2026-07-07T00:16:00.264091+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCAP67M6Q6LE","created_at":"2026-07-07T00:16:00.264091+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCAP67M6Q6LEEFMK","created_at":"2026-07-07T00:16:00.264091+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCAP67M6","created_at":"2026-07-07T00:16:00.264091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB","json":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB.json","graph_json":"https://pith.science/api/pith-number/SCAP67M6Q6LEEFMKRNA5CEDEQB/graph.json","events_json":"https://pith.science/api/pith-number/SCAP67M6Q6LEEFMKRNA5CEDEQB/events.json","paper":"https://pith.science/paper/SCAP67M6"},"agent_actions":{"view_html":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB","download_json":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB.json","view_paper":"https://pith.science/paper/SCAP67M6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02551&json=true","fetch_graph":"https://pith.science/api/pith-number/SCAP67M6Q6LEEFMKRNA5CEDEQB/graph.json","fetch_events":"https://pith.science/api/pith-number/SCAP67M6Q6LEEFMKRNA5CEDEQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB/action/storage_attestation","attest_author":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB/action/author_attestation","sign_citation":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB/action/citation_signature","submit_replication":"https://pith.science/pith/SCAP67M6Q6LEEFMKRNA5CEDEQB/action/replication_record"}},"created_at":"2026-07-07T00:16:00.264091+00:00","updated_at":"2026-07-07T00:16:00.264091+00:00"}