{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BJW5HVBJBCEMWZT6VIFIV2MAYV","short_pith_number":"pith:BJW5HVBJ","canonical_record":{"source":{"id":"2203.05465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T16:41:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"6801c84ffd06bcd0ed9158adb31176f4cb49c84f79ce19f0e0a148fb50bd555b","abstract_canon_sha256":"c9148f8bec820d6bb4722680208c683de57fb72e66f22e3a7a4381219c5c57a8"},"schema_version":"1.0"},"canonical_sha256":"0a6dd3d4290888cb667eaa0a8ae980c558786cedd06e19a22b53bae9fbb26284","source":{"kind":"arxiv","id":"2203.05465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.05465","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2203.05465v1","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05465","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"BJW5HVBJBCEM","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"BJW5HVBJBCEMWZT6","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"BJW5HVBJ","created_at":"2026-07-05T04:03:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BJW5HVBJBCEMWZT6VIFIV2MAYV","target":"record","payload":{"canonical_record":{"source":{"id":"2203.05465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T16:41:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"6801c84ffd06bcd0ed9158adb31176f4cb49c84f79ce19f0e0a148fb50bd555b","abstract_canon_sha256":"c9148f8bec820d6bb4722680208c683de57fb72e66f22e3a7a4381219c5c57a8"},"schema_version":"1.0"},"canonical_sha256":"0a6dd3d4290888cb667eaa0a8ae980c558786cedd06e19a22b53bae9fbb26284","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:41.710517Z","signature_b64":"9rU3AyU/XulfQEUl/okSwQ2NOogTPCc1KmXdqYji5GReN3n/GjWedxqYvPGPfZmTLlSMmA0utdljs5zBirCNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a6dd3d4290888cb667eaa0a8ae980c558786cedd06e19a22b53bae9fbb26284","last_reissued_at":"2026-07-05T04:03:41.710111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:41.710111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.05465","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":"2026-07-05T04:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zW4WbP+13wCtYDtSwDHNmN/FQ5GRb+iW+8kBMXEk2iSXnkS8gPinu330D8js4aYDx7DaZGjdrM/SMnUDooaUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T09:07:18.239066Z"},"content_sha256":"72c043034e940c9444f485d299c21226f682d361b7f834c2e0e3630d4605361c","schema_version":"1.0","event_id":"sha256:72c043034e940c9444f485d299c21226f682d361b7f834c2e0e3630d4605361c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BJW5HVBJBCEMWZT6VIFIV2MAYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Lei, Licheng Yu, Mengjiao Wang, Mohit Bansal, Ning Zhang, Tamara L. Berg, Xinlei Chen","submitted_at":"2022-03-10T16:41:12Z","abstract_excerpt":"Dual encoders and cross encoders have been widely used for image-text retrieval. Between the two, the dual encoder encodes the image and text independently followed by a dot product, while the cross encoder jointly feeds image and text as the input and performs dense multi-modal fusion. These two architectures are typically modeled separately without interaction. In this work, we propose LoopITR, which combines them in the same network for joint learning. Specifically, we let the dual encoder provide hard negatives to the cross encoder, and use the more discriminative cross encoder to distill "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05465","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/2203.05465/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":"2026-07-05T04:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPAAYpwz/C58akXFj7TcjINNVKBpFAI14x/4wH3wmdG748/UjdvUEVHxuqvQqtcwre3ngatG4NruK0c3Y6DpCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T09:07:18.239448Z"},"content_sha256":"826d17a1c95cc32065c93afb35862309798c45a1e16801fe51536932ca068ca0","schema_version":"1.0","event_id":"sha256:826d17a1c95cc32065c93afb35862309798c45a1e16801fe51536932ca068ca0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BJW5HVBJBCEMWZT6VIFIV2MAYV/bundle.json","state_url":"https://pith.science/pith/BJW5HVBJBCEMWZT6VIFIV2MAYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BJW5HVBJBCEMWZT6VIFIV2MAYV/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":"2026-07-09T09:07:18Z","links":{"resolver":"https://pith.science/pith/BJW5HVBJBCEMWZT6VIFIV2MAYV","bundle":"https://pith.science/pith/BJW5HVBJBCEMWZT6VIFIV2MAYV/bundle.json","state":"https://pith.science/pith/BJW5HVBJBCEMWZT6VIFIV2MAYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BJW5HVBJBCEMWZT6VIFIV2MAYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BJW5HVBJBCEMWZT6VIFIV2MAYV","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":"c9148f8bec820d6bb4722680208c683de57fb72e66f22e3a7a4381219c5c57a8","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T16:41:12Z","title_canon_sha256":"6801c84ffd06bcd0ed9158adb31176f4cb49c84f79ce19f0e0a148fb50bd555b"},"schema_version":"1.0","source":{"id":"2203.05465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.05465","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2203.05465v1","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05465","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"BJW5HVBJBCEM","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"BJW5HVBJBCEMWZT6","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"BJW5HVBJ","created_at":"2026-07-05T04:03:41Z"}],"graph_snapshots":[{"event_id":"sha256:826d17a1c95cc32065c93afb35862309798c45a1e16801fe51536932ca068ca0","target":"graph","created_at":"2026-07-05T04:03:41Z","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/2203.05465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dual encoders and cross encoders have been widely used for image-text retrieval. Between the two, the dual encoder encodes the image and text independently followed by a dot product, while the cross encoder jointly feeds image and text as the input and performs dense multi-modal fusion. These two architectures are typically modeled separately without interaction. In this work, we propose LoopITR, which combines them in the same network for joint learning. Specifically, we let the dual encoder provide hard negatives to the cross encoder, and use the more discriminative cross encoder to distill ","authors_text":"Jie Lei, Licheng Yu, Mengjiao Wang, Mohit Bansal, Ning Zhang, Tamara L. Berg, Xinlei Chen","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T16:41:12Z","title":"LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05465","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":"sha256:72c043034e940c9444f485d299c21226f682d361b7f834c2e0e3630d4605361c","target":"record","created_at":"2026-07-05T04:03:41Z","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":"c9148f8bec820d6bb4722680208c683de57fb72e66f22e3a7a4381219c5c57a8","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T16:41:12Z","title_canon_sha256":"6801c84ffd06bcd0ed9158adb31176f4cb49c84f79ce19f0e0a148fb50bd555b"},"schema_version":"1.0","source":{"id":"2203.05465","kind":"arxiv","version":1}},"canonical_sha256":"0a6dd3d4290888cb667eaa0a8ae980c558786cedd06e19a22b53bae9fbb26284","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a6dd3d4290888cb667eaa0a8ae980c558786cedd06e19a22b53bae9fbb26284","first_computed_at":"2026-07-05T04:03:41.710111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:03:41.710111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9rU3AyU/XulfQEUl/okSwQ2NOogTPCc1KmXdqYji5GReN3n/GjWedxqYvPGPfZmTLlSMmA0utdljs5zBirCNCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:03:41.710517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.05465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72c043034e940c9444f485d299c21226f682d361b7f834c2e0e3630d4605361c","sha256:826d17a1c95cc32065c93afb35862309798c45a1e16801fe51536932ca068ca0"],"state_sha256":"499144ecc2555d63fd9c9f814a0525ee362d268bd054844a74ac9c3e387c911d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+LmfVvoOZZCNtTqM2vSyRIrImK1X5IMTMqtpE1kl04jFdqbLXbuDmDmeFRSkAQbmgd3L2jA8ofMLA0NEx6YHBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T09:07:18.241555Z","bundle_sha256":"8c1377fd716859dc6afeb94b12ffa8ea0b9f1e90f9da9477ea6d00d462c78ca1"}}