{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BYROYUKBPAJW4JXG6CFIMB65SB","short_pith_number":"pith:BYROYUKB","canonical_record":{"source":{"id":"2507.17080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-22T23:45:43Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ef10f35ceae54cafb5aff08de4269641f051c6a367cfe1434c56a9b0fb7f16d4","abstract_canon_sha256":"b4d278095c0b2c2a4f226ee277a9695647d75b2f1c904d71264553ef3f145e91"},"schema_version":"1.0"},"canonical_sha256":"0e22ec514178136e26e6f08a8607dd9062be56bb2233f9fceb93ed4ff996829b","source":{"kind":"arxiv","id":"2507.17080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17080","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17080v1","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17080","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_12","alias_value":"BYROYUKBPAJW","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_16","alias_value":"BYROYUKBPAJW4JXG","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_8","alias_value":"BYROYUKB","created_at":"2026-07-05T11:42:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BYROYUKBPAJW4JXG6CFIMB65SB","target":"record","payload":{"canonical_record":{"source":{"id":"2507.17080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-22T23:45:43Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ef10f35ceae54cafb5aff08de4269641f051c6a367cfe1434c56a9b0fb7f16d4","abstract_canon_sha256":"b4d278095c0b2c2a4f226ee277a9695647d75b2f1c904d71264553ef3f145e91"},"schema_version":"1.0"},"canonical_sha256":"0e22ec514178136e26e6f08a8607dd9062be56bb2233f9fceb93ed4ff996829b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:01.280037Z","signature_b64":"YzDzSFJSAYJeWHDzqkF949N7QzyKXn5SvoZ8S3UhxM/QN//1+1VyAz1+YjswTSsoqJjMrNm6A9Ywlnt4E6/4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e22ec514178136e26e6f08a8607dd9062be56bb2233f9fceb93ed4ff996829b","last_reissued_at":"2026-07-05T11:42:01.279625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:01.279625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.17080","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UtES1TJxxnDnJY7rTVmwXBs0hr3RXAJXPQ5Jn/s9yCg8bMTX+BlDXJzByAzpIAJ9dxChxMd8o88or/IJDmunDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:49:45.500969Z"},"content_sha256":"7aa35cc4048411fc24f6682196ab89b5f952f5e27418180b343bde3f688fa1ff","schema_version":"1.0","event_id":"sha256:7aa35cc4048411fc24f6682196ab89b5f952f5e27418180b343bde3f688fa1ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BYROYUKBPAJW4JXG6CFIMB65SB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VL-CLIP: Enhancing Multimodal Recommendations via Visual Grounding and LLM-Augmented CLIP Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.IR","authors_text":"Evren Korpeoglu, Jianpeng Xu, Kai Zhao, Kannan Achan, Kehui Yao, Ramin Giahi, Sriram Kollipara, Topojoy Biswas, Vahid Mirjalili","submitted_at":"2025-07-22T23:45:43Z","abstract_excerpt":"Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce recommendation systems: 1) Weak object-level alignment, where global image embeddings fail to capture fine-grained product attributes, leading to suboptimal retrieval performance; 2) Ambiguous textual representations, where product descriptions often lack contextual clarity, affecting cross-modal matching; and 3) Domain mismatch, as generic vision-language mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17080","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/2507.17080/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sZdR/Rl4qqN93MfcTubJ4P9NoF2tCaGRlMMFRvH9bpcmVo9qXUc0MU4kPJPMB75b7efr0xo3NbaHQhfEg+TGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:49:45.501578Z"},"content_sha256":"282176e787631f77258ae561af7747f1b34d4b0446f046d9727ab114307c423d","schema_version":"1.0","event_id":"sha256:282176e787631f77258ae561af7747f1b34d4b0446f046d9727ab114307c423d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYROYUKBPAJW4JXG6CFIMB65SB/bundle.json","state_url":"https://pith.science/pith/BYROYUKBPAJW4JXG6CFIMB65SB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYROYUKBPAJW4JXG6CFIMB65SB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T14:49:45Z","links":{"resolver":"https://pith.science/pith/BYROYUKBPAJW4JXG6CFIMB65SB","bundle":"https://pith.science/pith/BYROYUKBPAJW4JXG6CFIMB65SB/bundle.json","state":"https://pith.science/pith/BYROYUKBPAJW4JXG6CFIMB65SB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYROYUKBPAJW4JXG6CFIMB65SB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BYROYUKBPAJW4JXG6CFIMB65SB","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":"b4d278095c0b2c2a4f226ee277a9695647d75b2f1c904d71264553ef3f145e91","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-22T23:45:43Z","title_canon_sha256":"ef10f35ceae54cafb5aff08de4269641f051c6a367cfe1434c56a9b0fb7f16d4"},"schema_version":"1.0","source":{"id":"2507.17080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17080","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17080v1","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17080","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_12","alias_value":"BYROYUKBPAJW","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_16","alias_value":"BYROYUKBPAJW4JXG","created_at":"2026-07-05T11:42:01Z"},{"alias_kind":"pith_short_8","alias_value":"BYROYUKB","created_at":"2026-07-05T11:42:01Z"}],"graph_snapshots":[{"event_id":"sha256:282176e787631f77258ae561af7747f1b34d4b0446f046d9727ab114307c423d","target":"graph","created_at":"2026-07-05T11:42:01Z","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/2507.17080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce recommendation systems: 1) Weak object-level alignment, where global image embeddings fail to capture fine-grained product attributes, leading to suboptimal retrieval performance; 2) Ambiguous textual representations, where product descriptions often lack contextual clarity, affecting cross-modal matching; and 3) Domain mismatch, as generic vision-language mo","authors_text":"Evren Korpeoglu, Jianpeng Xu, Kai Zhao, Kannan Achan, Kehui Yao, Ramin Giahi, Sriram Kollipara, Topojoy Biswas, Vahid Mirjalili","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-22T23:45:43Z","title":"VL-CLIP: Enhancing Multimodal Recommendations via Visual Grounding and LLM-Augmented CLIP Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17080","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":"sha256:7aa35cc4048411fc24f6682196ab89b5f952f5e27418180b343bde3f688fa1ff","target":"record","created_at":"2026-07-05T11:42:01Z","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":"b4d278095c0b2c2a4f226ee277a9695647d75b2f1c904d71264553ef3f145e91","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-22T23:45:43Z","title_canon_sha256":"ef10f35ceae54cafb5aff08de4269641f051c6a367cfe1434c56a9b0fb7f16d4"},"schema_version":"1.0","source":{"id":"2507.17080","kind":"arxiv","version":1}},"canonical_sha256":"0e22ec514178136e26e6f08a8607dd9062be56bb2233f9fceb93ed4ff996829b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e22ec514178136e26e6f08a8607dd9062be56bb2233f9fceb93ed4ff996829b","first_computed_at":"2026-07-05T11:42:01.279625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:01.279625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YzDzSFJSAYJeWHDzqkF949N7QzyKXn5SvoZ8S3UhxM/QN//1+1VyAz1+YjswTSsoqJjMrNm6A9Ywlnt4E6/4Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:01.280037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7aa35cc4048411fc24f6682196ab89b5f952f5e27418180b343bde3f688fa1ff","sha256:282176e787631f77258ae561af7747f1b34d4b0446f046d9727ab114307c423d"],"state_sha256":"9d76adfb30f3193e422960b5f11fc1138560f5d71a2830be22fe8e07ce824d74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQYejkRUD53BWUklF0gjo8VLwIr4esGOrilQhfB6HmjkyYwE4WsIa4NuBcgRb8ELqh1fk5Ucxb5FhDzcoBqFCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:49:45.504240Z","bundle_sha256":"a29130e4715cc9eaa6db20ba298dc1ec8c199c294437adc43cdc53dc1bf6cf81"}}