{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q56OF553UU77N3YCFSDP7KWWFD","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":"b270e89a8c91c34614a44460061563da9fe0983b184e0323ab070784f01508f8","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T14:07:20Z","title_canon_sha256":"34cf35ad5b5106e6537cd79bb700be08f9a01ee018e2daa7d09ff27c569f2527"},"schema_version":"1.0","source":{"id":"2605.18434","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18434","created_at":"2026-05-20T00:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18434v1","created_at":"2026-05-20T00:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18434","created_at":"2026-05-20T00:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"Q56OF553UU77","created_at":"2026-05-20T00:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"Q56OF553UU77N3YC","created_at":"2026-05-20T00:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"Q56OF553","created_at":"2026-05-20T00:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:17c61b63da0c0a78a68f67ee5f8ffb5cb6455a94eba7d2918f88bab3b594fb4c","target":"graph","created_at":"2026-05-20T00:06:00Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"TIGER-FG improves Recall@1 over the strongest baseline by 6.1 and 34.4 percentage points on the two evaluation benchmarks, respectively, with only 85.7M query-side parameters and 256-dim embeddings."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That item text descriptions provide reliable semantic guidance sufficient to produce target-focused representations implicitly, without explicit localization or detection, and that the dual distillation objectives will preserve both spatial consistency and similarity structure across varied item layouts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TIGER-FG proposes text-guided implicit fine-grained grounding with dual distillation to address modality and granularity asymmetries in image-to-multimodal e-commerce retrieval, reporting Recall@1 gains of 6.1 and 34.4 points on two new benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Item text can guide the creation of target-focused representations from full images to match cropped visual queries without object detection."}],"snapshot_sha256":"54d8b57e21efc56e5578e75491fe339e7f06980f68270cc7d3cc5ff9292ca1f4"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7a7b89de2f7841591d3427d3ba761a4d25e5da1ae37da8259f677e5619e4fc44"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T00:01:20.228987Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T00:00:55.631652Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T23:49:47.549594Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:27.568210Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"external_links","ran_at":"2026-05-19T23:31:32.146230Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T23:21:58.699669Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.650004Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18434/integrity.json","findings":[],"snapshot_sha256":"d5fdc3f39f5a86f548feec5608791756ce372f43f7b30a594a1009c97c8c046b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"E-commerce image search often takes a cropped image as the query, while each candidate is represented by full item images and structured text. This image-to-multimodal retrieval setting presents two asymmetries: a modality disparity -- a visual query must match image--text items, and a granularity disparity -- a cropped query must be compared with full images containing background context and possible distractors. Detection-based pipelines handle the granularity disparity through explicit localization but incur extra cost and error propagation, whereas CLIP-style encoders avoid detection, but ","authors_text":"Ben Chen, Chenyi Lei, Huangyu Dai, Lingtao Mao, Wenwu Ou, Xinyu Sun, Zexin Zheng, Zihan Liang","cross_cats":["cs.CV"],"headline":"Item text can guide the creation of target-focused representations from full images to match cropped visual queries without object detection.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T14:07:20Z","title":"TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval"},"references":{"count":19,"internal_anchors":7,"resolved_work":19,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"End-to-end object detection with transformers","work_id":"37ce22dc-54b4-462d-b1bf-6481e8136541","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Ben Chen, Linbo Jin, Xinxin Wang, Dehong Gao, Wen Jiang, and Wei Ning","work_id":"753c4c1a-6490-40d8-bd85-a6539f55d9fd","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Category-oriented representation learning for image to multi-modal retrieval.arXiv preprint arXiv:2305.03972,","work_id":"6dc6f514-1c31-42d7-9454-0bd2091678ee","year":null},{"cited_arxiv_id":"2309.16588","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Vision Transformers Need Registers","work_id":"57106da4-5420-4778-94eb-e821589aa7a0","year":null},{"cited_arxiv_id":"2401.08281","doi":"","is_internal_anchor":true,"ref_index":6,"title":"The Faiss library","work_id":"41b4c732-3a63-4106-9e7c-50d61cfb2126","year":null}],"snapshot_sha256":"7964f028db8911b7afd6c75eeef25bf55851ffb7e0296b4d57d9163fb1baf007"},"source":{"id":"2605.18434","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T23:51:00.345273Z","id":"83dc678e-3ee3-4925-87f2-4e6a01ff738e","model_set":{"reader":"grok-4.3"},"one_line_summary":"TIGER-FG proposes text-guided implicit fine-grained grounding with dual distillation to address modality and granularity asymmetries in image-to-multimodal e-commerce retrieval, reporting Recall@1 gains of 6.1 and 34.4 points on two new benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Item text can guide the creation of target-focused representations from full images to match cropped visual queries without object detection.","strongest_claim":"TIGER-FG improves Recall@1 over the strongest baseline by 6.1 and 34.4 percentage points on the two evaluation benchmarks, respectively, with only 85.7M query-side parameters and 256-dim embeddings.","weakest_assumption":"That item text descriptions provide reliable semantic guidance sufficient to produce target-focused representations implicitly, without explicit localization or detection, and that the dual distillation objectives will preserve both spatial consistency and similarity structure across varied item layouts."}},"verdict_id":"83dc678e-3ee3-4925-87f2-4e6a01ff738e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9bcc994758003ad6120e053ba349a13435e186fd49294f3fb8dd32de4d737ad1","target":"record","created_at":"2026-05-20T00:06:00Z","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":"b270e89a8c91c34614a44460061563da9fe0983b184e0323ab070784f01508f8","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T14:07:20Z","title_canon_sha256":"34cf35ad5b5106e6537cd79bb700be08f9a01ee018e2daa7d09ff27c569f2527"},"schema_version":"1.0","source":{"id":"2605.18434","kind":"arxiv","version":1}},"canonical_sha256":"877ce2f7bba53ff6ef022c86ffaad628c125d243a197d64e833c17f6b93486b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"877ce2f7bba53ff6ef022c86ffaad628c125d243a197d64e833c17f6b93486b6","first_computed_at":"2026-05-20T00:06:00.782578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:00.782578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GAF49ozVGSzYQnE381uX4vAjGRBmMb3WuFAhvWBOBateLFgJJ2jbZ0Bgj6CbLI3+1QKKr6d5Wfzsh5DtCEfuAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:00.783448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18434","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bcc994758003ad6120e053ba349a13435e186fd49294f3fb8dd32de4d737ad1","sha256:17c61b63da0c0a78a68f67ee5f8ffb5cb6455a94eba7d2918f88bab3b594fb4c"],"state_sha256":"779f31da6873218a5f8ad551f1fa2749deb823933cc3d5e11fe248f8d8e33f13"}