{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JAFZYQW5X75FGBBQ2QNN6VN4RZ","short_pith_number":"pith:JAFZYQW5","canonical_record":{"source":{"id":"2412.13364","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T22:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"cdbf33f72bbc78d18195393b5e252bc1290d21b8a01f28fa2568245305d1d775","abstract_canon_sha256":"a35f1742ce76e9b14c5ac30742ddc01a7f2a99069341cde3e09a62def72b487a"},"schema_version":"1.0"},"canonical_sha256":"480b9c42ddbffa530430d41adf55bc8e5e99280079056b7ca8b70a9fc60f965b","source":{"kind":"arxiv","id":"2412.13364","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13364","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13364v1","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13364","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"pith_short_12","alias_value":"JAFZYQW5X75F","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"pith_short_16","alias_value":"JAFZYQW5X75FGBBQ","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"pith_short_8","alias_value":"JAFZYQW5","created_at":"2026-07-05T09:51:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JAFZYQW5X75FGBBQ2QNN6VN4RZ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13364","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T22:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"cdbf33f72bbc78d18195393b5e252bc1290d21b8a01f28fa2568245305d1d775","abstract_canon_sha256":"a35f1742ce76e9b14c5ac30742ddc01a7f2a99069341cde3e09a62def72b487a"},"schema_version":"1.0"},"canonical_sha256":"480b9c42ddbffa530430d41adf55bc8e5e99280079056b7ca8b70a9fc60f965b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:00.432558Z","signature_b64":"IPg33pLsakfpcNZmr6fqrDKk9EC5BeUxVAsC5k6yxSua6HasAVgKcwM36fbSbRGIiN2o6cJx6P/6WgtiLhmKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"480b9c42ddbffa530430d41adf55bc8e5e99280079056b7ca8b70a9fc60f965b","last_reissued_at":"2026-07-05T09:51:00.431976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:00.431976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13364","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":"2026-07-05T09:51:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hE17XRSXLkCR1ulrYXDAjb1NB3reN2Ek4UYXkEgd0eSoigaXbVBx1xkYJ2JE1RLBKOfTtbfKPSJUI94WV23gCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T11:29:34.589385Z"},"content_sha256":"53359d77fb03f0945da3d863b631a899624c50e7afc651b10c366ec66d7d440a","schema_version":"1.0","event_id":"sha256:53359d77fb03f0945da3d863b631a899624c50e7afc651b10c366ec66d7d440a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JAFZYQW5X75FGBBQ2QNN6VN4RZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bringing Multimodality to Amazon Visual Search System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anuj Bindal, Arnab Dhua, Benjamin Yao, Doug Gray, Han Ding, Jinyu Yang, Kelvin Chen, Michael Huang, Ouye Xie, Son Tran, Tal Neiman, Tao Zhou, Xinliang Zhu","submitted_at":"2024-12-17T22:45:25Z","abstract_excerpt":"Image to image matching has been well studied in the computer vision community. Previous studies mainly focus on training a deep metric learning model matching visual patterns between the query image and gallery images. In this study, we show that pure image-to-image matching suffers from false positives caused by matching to local visual patterns. To alleviate this issue, we propose to leverage recent advances in vision-language pretraining research. Specifically, we introduce additional image-text alignment losses into deep metric learning, which serve as constraints to the image-to-image ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13364","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/2412.13364/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":"2026-07-05T09:51:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1V/oNQH1SlVHTfa0jNbRKN5jryFx6ArmINMsn7iiIBbWO3utykmZGoLNJArP0GgtEJEp/CaEGKNg/149aZZBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T11:29:34.590307Z"},"content_sha256":"7aac253b7843e0bb0e14d10343f9aee605662b23b2034197b22a607a663d2a6c","schema_version":"1.0","event_id":"sha256:7aac253b7843e0bb0e14d10343f9aee605662b23b2034197b22a607a663d2a6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAFZYQW5X75FGBBQ2QNN6VN4RZ/bundle.json","state_url":"https://pith.science/pith/JAFZYQW5X75FGBBQ2QNN6VN4RZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAFZYQW5X75FGBBQ2QNN6VN4RZ/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":"2026-08-14T11:29:34Z","links":{"resolver":"https://pith.science/pith/JAFZYQW5X75FGBBQ2QNN6VN4RZ","bundle":"https://pith.science/pith/JAFZYQW5X75FGBBQ2QNN6VN4RZ/bundle.json","state":"https://pith.science/pith/JAFZYQW5X75FGBBQ2QNN6VN4RZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAFZYQW5X75FGBBQ2QNN6VN4RZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JAFZYQW5X75FGBBQ2QNN6VN4RZ","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":"a35f1742ce76e9b14c5ac30742ddc01a7f2a99069341cde3e09a62def72b487a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T22:45:25Z","title_canon_sha256":"cdbf33f72bbc78d18195393b5e252bc1290d21b8a01f28fa2568245305d1d775"},"schema_version":"1.0","source":{"id":"2412.13364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13364","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13364v1","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13364","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"pith_short_12","alias_value":"JAFZYQW5X75F","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"pith_short_16","alias_value":"JAFZYQW5X75FGBBQ","created_at":"2026-07-05T09:51:00Z"},{"alias_kind":"pith_short_8","alias_value":"JAFZYQW5","created_at":"2026-07-05T09:51:00Z"}],"graph_snapshots":[{"event_id":"sha256:7aac253b7843e0bb0e14d10343f9aee605662b23b2034197b22a607a663d2a6c","target":"graph","created_at":"2026-07-05T09:51:00Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.13364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image to image matching has been well studied in the computer vision community. Previous studies mainly focus on training a deep metric learning model matching visual patterns between the query image and gallery images. In this study, we show that pure image-to-image matching suffers from false positives caused by matching to local visual patterns. To alleviate this issue, we propose to leverage recent advances in vision-language pretraining research. Specifically, we introduce additional image-text alignment losses into deep metric learning, which serve as constraints to the image-to-image ma","authors_text":"Anuj Bindal, Arnab Dhua, Benjamin Yao, Doug Gray, Han Ding, Jinyu Yang, Kelvin Chen, Michael Huang, Ouye Xie, Son Tran, Tal Neiman, Tao Zhou, Xinliang Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T22:45:25Z","title":"Bringing Multimodality to Amazon Visual Search System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13364","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":"sha256:53359d77fb03f0945da3d863b631a899624c50e7afc651b10c366ec66d7d440a","target":"record","created_at":"2026-07-05T09:51:00Z","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":"a35f1742ce76e9b14c5ac30742ddc01a7f2a99069341cde3e09a62def72b487a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T22:45:25Z","title_canon_sha256":"cdbf33f72bbc78d18195393b5e252bc1290d21b8a01f28fa2568245305d1d775"},"schema_version":"1.0","source":{"id":"2412.13364","kind":"arxiv","version":1}},"canonical_sha256":"480b9c42ddbffa530430d41adf55bc8e5e99280079056b7ca8b70a9fc60f965b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"480b9c42ddbffa530430d41adf55bc8e5e99280079056b7ca8b70a9fc60f965b","first_computed_at":"2026-07-05T09:51:00.431976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:00.431976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IPg33pLsakfpcNZmr6fqrDKk9EC5BeUxVAsC5k6yxSua6HasAVgKcwM36fbSbRGIiN2o6cJx6P/6WgtiLhmKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:00.432558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53359d77fb03f0945da3d863b631a899624c50e7afc651b10c366ec66d7d440a","sha256:7aac253b7843e0bb0e14d10343f9aee605662b23b2034197b22a607a663d2a6c"],"state_sha256":"a9d150c5e27234ac651124db0838023c2b8c5567045c239156ab787a75f64d5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6RuMtSavXb4B77lGou0KuUpAj1iuM98ehaWxo7WiaYnisim9UDipzdgnjp+JNTftAK1ww6/O/ybctnYhnAPkAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T11:29:34.627762Z","bundle_sha256":"638fc3307f5591e6f59c8af29bcf4d192e1220dd7dcc419aeef8a8249aa48a6a"}}