{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H3YYG3OQRUFLM65PAFKTRDDUXK","short_pith_number":"pith:H3YYG3OQ","schema_version":"1.0","canonical_sha256":"3ef1836dd08d0ab67baf0155388c74ba89c66bf17e3ea954df16d66f4a93d52a","source":{"kind":"arxiv","id":"2605.26933","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, De Wen Soh, Junsong Yuan, Zhengbo Zhang, Zhigang Tu","submitted_at":"2026-05-26T12:26:56Z","abstract_excerpt":"Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often struggle in scenarios that demand fine-grained understanding of semantic and visual structural information within video frames. Text-to-image diffusion models are well known for their ability to generate images that accurately reflect the semantics and structures described in the input prompt, demonstrating a strong grasp of visual semantics and structures."},"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":"2605.26933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T12:26:56Z","cross_cats_sorted":[],"title_canon_sha256":"880adc797d9720e12901e9102208da7c58804ce9a5f1ecc2dc07faf5cbd57c7b","abstract_canon_sha256":"065a3db2a36f20a1c0e551581ff137bfb10690e3a1cad343bab76258ae2030b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:20.597705Z","signature_b64":"j2OJ/vtEGAfI6lX4ynwkVp6HDDDvC/ZjXeJXXo6jxtXHAjwIQwoPuHIBNT6dbWp8O1YMO3fTyhGTKF4Jbga/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ef1836dd08d0ab67baf0155388c74ba89c66bf17e3ea954df16d66f4a93d52a","last_reissued_at":"2026-05-27T01:06:20.597122Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:20.597122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, De Wen Soh, Junsong Yuan, Zhengbo Zhang, Zhigang Tu","submitted_at":"2026-05-26T12:26:56Z","abstract_excerpt":"Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often struggle in scenarios that demand fine-grained understanding of semantic and visual structural information within video frames. Text-to-image diffusion models are well known for their ability to generate images that accurately reflect the semantics and structures described in the input prompt, demonstrating a strong grasp of visual semantics and structures."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26933","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/2605.26933/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":"2605.26933","created_at":"2026-05-27T01:06:20.597219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26933v1","created_at":"2026-05-27T01:06:20.597219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26933","created_at":"2026-05-27T01:06:20.597219+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3YYG3OQRUFL","created_at":"2026-05-27T01:06:20.597219+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3YYG3OQRUFLM65P","created_at":"2026-05-27T01:06:20.597219+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3YYG3OQ","created_at":"2026-05-27T01:06:20.597219+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/H3YYG3OQRUFLM65PAFKTRDDUXK","json":"https://pith.science/pith/H3YYG3OQRUFLM65PAFKTRDDUXK.json","graph_json":"https://pith.science/api/pith-number/H3YYG3OQRUFLM65PAFKTRDDUXK/graph.json","events_json":"https://pith.science/api/pith-number/H3YYG3OQRUFLM65PAFKTRDDUXK/events.json","paper":"https://pith.science/paper/H3YYG3OQ"},"agent_actions":{"view_html":"https://pith.science/pith/H3YYG3OQRUFLM65PAFKTRDDUXK","download_json":"https://pith.science/pith/H3YYG3OQRUFLM65PAFKTRDDUXK.json","view_paper":"https://pith.science/paper/H3YYG3OQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26933&json=true","fetch_graph":"https://pith.science/api/pith-number/H3YYG3OQRUFLM65PAFKTRDDUXK/graph.json","fetch_events":"https://pith.science/api/pith-number/H3YYG3OQRUFLM65PAFKTRDDUXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3YYG3OQRUFLM65PAFKTRDDUXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3YYG3OQRUFLM65PAFKTRDDUXK/action/storage_attestation","attest_author":"https://pith.science/pith/H3YYG3OQRUFLM65PAFKTRDDUXK/action/author_attestation","sign_citation":"https://pith.science/pith/H3YYG3OQRUFLM65PAFKTRDDUXK/action/citation_signature","submit_replication":"https://pith.science/pith/H3YYG3OQRUFLM65PAFKTRDDUXK/action/replication_record"}},"created_at":"2026-05-27T01:06:20.597219+00:00","updated_at":"2026-05-27T01:06:20.597219+00:00"}