{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XY2FZJZLAAPUQDTLSO7M55NOVN","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":"be427863419199cd386b25d423e89a95d56a59ca767fdeddd7f9dea672399a07","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T13:11:40Z","title_canon_sha256":"231cfc607e17f4f8761cb09e1c4265cb2902d9aa059ed5bd7fc019e06be03195"},"schema_version":"1.0","source":{"id":"2508.04424","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04424","created_at":"2026-06-19T16:12:47Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04424v3","created_at":"2026-06-19T16:12:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04424","created_at":"2026-06-19T16:12:47Z"},{"alias_kind":"pith_short_12","alias_value":"XY2FZJZLAAPU","created_at":"2026-06-19T16:12:47Z"},{"alias_kind":"pith_short_16","alias_value":"XY2FZJZLAAPUQDTL","created_at":"2026-06-19T16:12:47Z"},{"alias_kind":"pith_short_8","alias_value":"XY2FZJZL","created_at":"2026-06-19T16:12:47Z"}],"graph_snapshots":[{"event_id":"sha256:29e354c4f89761b211f814eb68e3629b05d0b2b36c6e71e29ea9d2eb4855b45a","target":"graph","created_at":"2026-06-19T16:12:47Z","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/2508.04424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieving fine-grained visual content based on user intent remains a challenge in multimodal systems. Although current Composed Image Retrieval (CIR) methods combine reference images with retrieval texts, they are constrained to image-level matching and cannot localize specific objects. To this end, we propose Composed Object Retrieval (COR), a new object-level retrieval task that retrieves target object(s) from candidate objects in a target image and grounds the retrieved result with pixel-level masks. Given a reference object, its mask, a target image, and a retrieval text describing the de","authors_text":"Fahad Shahbaz Khan, Guanyu Yang, Jinxing Zhou, Nian Liu, Salman Khan, Tong Wang, Zongyan Han","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T13:11:40Z","title":"Composed Object Retrieval: Object-level Retrieval via Composed Expressions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04424","kind":"arxiv","version":3},"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":"sha256:5cde316131209c8503cd70b03feec2ab28bee4b3c4f3bccc33452fd176164326","target":"record","created_at":"2026-06-19T16:12:47Z","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":"be427863419199cd386b25d423e89a95d56a59ca767fdeddd7f9dea672399a07","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T13:11:40Z","title_canon_sha256":"231cfc607e17f4f8761cb09e1c4265cb2902d9aa059ed5bd7fc019e06be03195"},"schema_version":"1.0","source":{"id":"2508.04424","kind":"arxiv","version":3}},"canonical_sha256":"be345ca72b001f480e6b93becef5aeab4edcb61218d10404b37bfdf27297f2b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be345ca72b001f480e6b93becef5aeab4edcb61218d10404b37bfdf27297f2b5","first_computed_at":"2026-06-19T16:12:47.169232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:47.169232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SM0hFWqy5B3KdGxDmH3dv7gTFvwcAO9D78s9sQ0EssFyotUSHCnM2ACT96NNjikaPF0nBsTdaaPdsHYp4eszAw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:47.169716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04424","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cde316131209c8503cd70b03feec2ab28bee4b3c4f3bccc33452fd176164326","sha256:29e354c4f89761b211f814eb68e3629b05d0b2b36c6e71e29ea9d2eb4855b45a"],"state_sha256":"33d53384a1448e4c3235621fd47678ffbd11d56e9d7fbff04fa5ad591979c941"}