{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XLE3YY3WRNLYD5C4UYPG5W3JTO","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":"12d6b8a67c4b1da099c5945e9983e6cd2401c92f07820c0c7c59c0b794a1248e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T23:02:26Z","title_canon_sha256":"ffe556895136fa7371ab43aad8cf6be3d31ad34ec54d8198cbd9547c1f5a53cb"},"schema_version":"1.0","source":{"id":"2308.16354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16354","created_at":"2026-07-05T06:46:26Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16354v1","created_at":"2026-07-05T06:46:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16354","created_at":"2026-07-05T06:46:26Z"},{"alias_kind":"pith_short_12","alias_value":"XLE3YY3WRNLY","created_at":"2026-07-05T06:46:26Z"},{"alias_kind":"pith_short_16","alias_value":"XLE3YY3WRNLYD5C4","created_at":"2026-07-05T06:46:26Z"},{"alias_kind":"pith_short_8","alias_value":"XLE3YY3W","created_at":"2026-07-05T06:46:26Z"}],"graph_snapshots":[{"event_id":"sha256:17bf7e1242bbde17eba43610b8b45f95fa7540598109457524909a7fff700b11","target":"graph","created_at":"2026-07-05T06:46:26Z","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/2308.16354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Catalog Phrase Grounding (CPG), a model that can associate product textual data (title, brands) into corresponding regions of product images (isolated product region, brand logo region) for e-commerce vision-language applications. We use a state-of-the-art modulated multimodal transformer encoder-decoder architecture unifying object detection and phrase-grounding. We train the model in self-supervised fashion with 2.3 million image-text pairs synthesized from an e-commerce site. The self-supervision data is annotated with high-confidence pseudo-labels generated with a combination of","authors_text":"Ismail Tutar, Karim Bouyarmane, Wenyi Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T23:02:26Z","title":"Catalog Phrase Grounding (CPG): Grounding of Product Textual Attributes in Product Images for e-commerce Vision-Language Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16354","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":"sha256:0858188112db1d29dbea70885784bef6102a6b335e1480809b8766cef2df5fe5","target":"record","created_at":"2026-07-05T06:46:26Z","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":"12d6b8a67c4b1da099c5945e9983e6cd2401c92f07820c0c7c59c0b794a1248e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T23:02:26Z","title_canon_sha256":"ffe556895136fa7371ab43aad8cf6be3d31ad34ec54d8198cbd9547c1f5a53cb"},"schema_version":"1.0","source":{"id":"2308.16354","kind":"arxiv","version":1}},"canonical_sha256":"bac9bc63768b5781f45ca61e6edb699bbb24ee268d8560b158729ba9fec78e79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bac9bc63768b5781f45ca61e6edb699bbb24ee268d8560b158729ba9fec78e79","first_computed_at":"2026-07-05T06:46:26.610913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:26.610913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zHN9qaOZpHNHG53EPsYtA8hhmI4tDaIedZPWbewgdyoB4Rt0imLG7NufWL2VHI2Axe3Ufu6SjS8b3LaowD+qAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:26.611310Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0858188112db1d29dbea70885784bef6102a6b335e1480809b8766cef2df5fe5","sha256:17bf7e1242bbde17eba43610b8b45f95fa7540598109457524909a7fff700b11"],"state_sha256":"6fadbce46faa4f0db9a7f7ac3129a90d6874b61ba7ec794c7853d4bb002b38dc"}