{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CGQZJ6RIDDWQHEPOI56KG2ZQYW","short_pith_number":"pith:CGQZJ6RI","canonical_record":{"source":{"id":"2112.11294","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:33:23Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"aadd78d8afc7a9e7202d22ab45d4e8a74b74da453ba2ea158e756f018db9c3d8","abstract_canon_sha256":"07545afefbcd4d6e7ad337a266b360a53a60618203b7ceeb6ff814db5e01e998"},"schema_version":"1.0"},"canonical_sha256":"11a194fa2818ed0391ee477ca36b30c5a526adef37976686b61c1610baa18f15","source":{"kind":"arxiv","id":"2112.11294","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11294","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11294v2","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11294","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"CGQZJ6RIDDWQ","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"CGQZJ6RIDDWQHEPO","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"CGQZJ6RI","created_at":"2026-07-05T03:45:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CGQZJ6RIDDWQHEPOI56KG2ZQYW","target":"record","payload":{"canonical_record":{"source":{"id":"2112.11294","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:33:23Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"aadd78d8afc7a9e7202d22ab45d4e8a74b74da453ba2ea158e756f018db9c3d8","abstract_canon_sha256":"07545afefbcd4d6e7ad337a266b360a53a60618203b7ceeb6ff814db5e01e998"},"schema_version":"1.0"},"canonical_sha256":"11a194fa2818ed0391ee477ca36b30c5a526adef37976686b61c1610baa18f15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:12.890864Z","signature_b64":"5wiwtXJ7CMN9e02AWtIVIyNvXqsGzs26AtfjgXhDNGLKtpI3VGg1UQX00CPX6svxZPYiWCNzXEzaUHkP4mZ+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11a194fa2818ed0391ee477ca36b30c5a526adef37976686b61c1610baa18f15","last_reissued_at":"2026-07-05T03:45:12.890406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:12.890406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.11294","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3jvyYLylE2mIYi75Xy1vcMEewCaqw41OGAO/fnKNZDJCTPMA5Qm07KaQjeiYeWYtobda+p8pQPtM8irHi0ACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:10:34.592224Z"},"content_sha256":"e5c02fe937124390addabfa9502048fdee365693b5ee2c6fe60c940596a8e5d2","schema_version":"1.0","event_id":"sha256:e5c02fe937124390addabfa9502048fdee365693b5ee2c6fe60c940596a8e5d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CGQZJ6RIDDWQHEPOI56KG2ZQYW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extending CLIP for Category-to-image Retrieval in E-commerce","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"Ernst Kuiper, Maarten de Rijke, Mariya Hendriksen, Maurits Bleeker, Nanne van Noord, Svitlana Vakulenko","submitted_at":"2021-12-21T15:33:23Z","abstract_excerpt":"E-commerce provides rich multimodal data that is barely leveraged in practice. One aspect of this data is a category tree that is being used in search and recommendation. However, in practice, during a user's session there is often a mismatch between a textual and a visual representation of a given category. Motivated by the problem, we introduce the task of category-to-image retrieval in e-commerce and propose a model for the task, CLIP-ITA. The model leverages information from multiple modalities (textual, visual, and attribute modality) to create product representations. We explore how addi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11294","kind":"arxiv","version":2},"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/2112.11294/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":"2026-07-05T03:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oMOXOinqtkqlKgSJUwUv6wDSlvUSNgGeg2A/9hqIVvEULxVjp98Aug1eyUT40CZdJFm+AbPoMlVxF7gf93+DAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:10:34.593151Z"},"content_sha256":"8833e624052f586bebb897b533056dc437a620653a63ecb0d1f49ee5089069c8","schema_version":"1.0","event_id":"sha256:8833e624052f586bebb897b533056dc437a620653a63ecb0d1f49ee5089069c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/bundle.json","state_url":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/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":"2026-08-16T07:10:34Z","links":{"resolver":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW","bundle":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/bundle.json","state":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CGQZJ6RIDDWQHEPOI56KG2ZQYW","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":"07545afefbcd4d6e7ad337a266b360a53a60618203b7ceeb6ff814db5e01e998","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:33:23Z","title_canon_sha256":"aadd78d8afc7a9e7202d22ab45d4e8a74b74da453ba2ea158e756f018db9c3d8"},"schema_version":"1.0","source":{"id":"2112.11294","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11294","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11294v2","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11294","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"CGQZJ6RIDDWQ","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"CGQZJ6RIDDWQHEPO","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"CGQZJ6RI","created_at":"2026-07-05T03:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:8833e624052f586bebb897b533056dc437a620653a63ecb0d1f49ee5089069c8","target":"graph","created_at":"2026-07-05T03:45:12Z","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/2112.11294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"E-commerce provides rich multimodal data that is barely leveraged in practice. One aspect of this data is a category tree that is being used in search and recommendation. However, in practice, during a user's session there is often a mismatch between a textual and a visual representation of a given category. Motivated by the problem, we introduce the task of category-to-image retrieval in e-commerce and propose a model for the task, CLIP-ITA. The model leverages information from multiple modalities (textual, visual, and attribute modality) to create product representations. We explore how addi","authors_text":"Ernst Kuiper, Maarten de Rijke, Mariya Hendriksen, Maurits Bleeker, Nanne van Noord, Svitlana Vakulenko","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:33:23Z","title":"Extending CLIP for Category-to-image Retrieval in E-commerce"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11294","kind":"arxiv","version":2},"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:e5c02fe937124390addabfa9502048fdee365693b5ee2c6fe60c940596a8e5d2","target":"record","created_at":"2026-07-05T03:45:12Z","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":"07545afefbcd4d6e7ad337a266b360a53a60618203b7ceeb6ff814db5e01e998","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:33:23Z","title_canon_sha256":"aadd78d8afc7a9e7202d22ab45d4e8a74b74da453ba2ea158e756f018db9c3d8"},"schema_version":"1.0","source":{"id":"2112.11294","kind":"arxiv","version":2}},"canonical_sha256":"11a194fa2818ed0391ee477ca36b30c5a526adef37976686b61c1610baa18f15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11a194fa2818ed0391ee477ca36b30c5a526adef37976686b61c1610baa18f15","first_computed_at":"2026-07-05T03:45:12.890406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:12.890406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5wiwtXJ7CMN9e02AWtIVIyNvXqsGzs26AtfjgXhDNGLKtpI3VGg1UQX00CPX6svxZPYiWCNzXEzaUHkP4mZ+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:12.890864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.11294","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5c02fe937124390addabfa9502048fdee365693b5ee2c6fe60c940596a8e5d2","sha256:8833e624052f586bebb897b533056dc437a620653a63ecb0d1f49ee5089069c8"],"state_sha256":"58ef365698cf1ccbd952aa59ff5ae66b823d24499bf0c1dee87e0db45f0aef6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W7e9lg7GG6bEkEqfdJjagpG4FUnUYvKcDqncY943UkGPC6X0D4cOwrdqBbN52o4kZMhko0Kjhvq/yRisO7ZlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:10:34.598199Z","bundle_sha256":"1fc1b1bb0648c74947e6ca3f90862ee0639ce400a90edb8b2b810234501f504f"}}