{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CL74TYX6RWENGKAVSDKTZLVTWP","short_pith_number":"pith:CL74TYX6","canonical_record":{"source":{"id":"2102.04980","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T17:54:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4e9fb202bb091685bb4534e8cae48e97ea85864c031f6bea6b2d75ce0311ab7e","abstract_canon_sha256":"5106c78dbfa6a09226cad6ed291d5ce84dc84e623db64831c37aedc39c8a9c67"},"schema_version":"1.0"},"canonical_sha256":"12ffc9e2fe8d88d3281590d53caeb3b3cd37b5480646f41fb58559b92161f73a","source":{"kind":"arxiv","id":"2102.04980","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04980","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04980v3","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04980","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"pith_short_12","alias_value":"CL74TYX6RWEN","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"pith_short_16","alias_value":"CL74TYX6RWENGKAV","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"pith_short_8","alias_value":"CL74TYX6","created_at":"2026-07-05T03:08:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CL74TYX6RWENGKAVSDKTZLVTWP","target":"record","payload":{"canonical_record":{"source":{"id":"2102.04980","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T17:54:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4e9fb202bb091685bb4534e8cae48e97ea85864c031f6bea6b2d75ce0311ab7e","abstract_canon_sha256":"5106c78dbfa6a09226cad6ed291d5ce84dc84e623db64831c37aedc39c8a9c67"},"schema_version":"1.0"},"canonical_sha256":"12ffc9e2fe8d88d3281590d53caeb3b3cd37b5480646f41fb58559b92161f73a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:43.959698Z","signature_b64":"bXPVv1kGF8JpHIBNz5l+lI11GNS6gtwslr/tY+KLvaUZ2yumixlFDjoW66bXRhFMHvbTxTniGN7LwV23qSB9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ffc9e2fe8d88d3281590d53caeb3b3cd37b5480646f41fb58559b92161f73a","last_reissued_at":"2026-07-05T03:08:43.959266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:43.959266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.04980","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:08:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fyHnC/lzbwVJ8clu73iN3rjkAIMlbU3Q0qHIWbhdhnmmxbwVk70VAUbgouZTzqYq65Y0YPSnI3Wipij+fTzGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T11:09:35.322395Z"},"content_sha256":"74ace362e93509501031746ef832bb69b41c343f7fc58e7db9f34517d5da9838","schema_version":"1.0","event_id":"sha256:74ace362e93509501031746ef832bb69b41c343f7fc58e7db9f34517d5da9838"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CL74TYX6RWENGKAVSDKTZLVTWP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jordi Pont-Tuset, Radu Soricut, Soravit Changpinyo, Vittorio Ferrari","submitted_at":"2021-02-09T17:54:34Z","abstract_excerpt":"Most existing image retrieval systems use text queries as a way for the user to express what they are looking for. However, fine-grained image retrieval often requires the ability to also express where in the image the content they are looking for is. The text modality can only cumbersomely express such localization preferences, whereas pointing is a more natural fit. In this paper, we propose an image retrieval setup with a new form of multimodal queries, where the user simultaneously uses both spoken natural language (the what) and mouse traces over an empty canvas (the where) to express the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04980","kind":"arxiv","version":3},"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/2102.04980/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":"2026-07-05T03:08:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fr+akzUAA7mZGMvj8LEDgNJ5Gw1Irt64+XnbyuQmj2AC8BJngGj4dNdvRPUFzEyyA2pR9pHJlCpixIWFDlj6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T11:09:35.322761Z"},"content_sha256":"0c3d94c5da7444a0774d085aa1812e6ce2c55bb89a6b53c856a3e3c6243b42e6","schema_version":"1.0","event_id":"sha256:0c3d94c5da7444a0774d085aa1812e6ce2c55bb89a6b53c856a3e3c6243b42e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CL74TYX6RWENGKAVSDKTZLVTWP/bundle.json","state_url":"https://pith.science/pith/CL74TYX6RWENGKAVSDKTZLVTWP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CL74TYX6RWENGKAVSDKTZLVTWP/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":"2026-07-15T11:09:35Z","links":{"resolver":"https://pith.science/pith/CL74TYX6RWENGKAVSDKTZLVTWP","bundle":"https://pith.science/pith/CL74TYX6RWENGKAVSDKTZLVTWP/bundle.json","state":"https://pith.science/pith/CL74TYX6RWENGKAVSDKTZLVTWP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CL74TYX6RWENGKAVSDKTZLVTWP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CL74TYX6RWENGKAVSDKTZLVTWP","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":"5106c78dbfa6a09226cad6ed291d5ce84dc84e623db64831c37aedc39c8a9c67","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T17:54:34Z","title_canon_sha256":"4e9fb202bb091685bb4534e8cae48e97ea85864c031f6bea6b2d75ce0311ab7e"},"schema_version":"1.0","source":{"id":"2102.04980","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04980","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04980v3","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04980","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"pith_short_12","alias_value":"CL74TYX6RWEN","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"pith_short_16","alias_value":"CL74TYX6RWENGKAV","created_at":"2026-07-05T03:08:43Z"},{"alias_kind":"pith_short_8","alias_value":"CL74TYX6","created_at":"2026-07-05T03:08:43Z"}],"graph_snapshots":[{"event_id":"sha256:0c3d94c5da7444a0774d085aa1812e6ce2c55bb89a6b53c856a3e3c6243b42e6","target":"graph","created_at":"2026-07-05T03:08:43Z","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/2102.04980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing image retrieval systems use text queries as a way for the user to express what they are looking for. However, fine-grained image retrieval often requires the ability to also express where in the image the content they are looking for is. The text modality can only cumbersomely express such localization preferences, whereas pointing is a more natural fit. In this paper, we propose an image retrieval setup with a new form of multimodal queries, where the user simultaneously uses both spoken natural language (the what) and mouse traces over an empty canvas (the where) to express the","authors_text":"Jordi Pont-Tuset, Radu Soricut, Soravit Changpinyo, Vittorio Ferrari","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T17:54:34Z","title":"Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04980","kind":"arxiv","version":3},"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":"sha256:74ace362e93509501031746ef832bb69b41c343f7fc58e7db9f34517d5da9838","target":"record","created_at":"2026-07-05T03:08:43Z","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":"5106c78dbfa6a09226cad6ed291d5ce84dc84e623db64831c37aedc39c8a9c67","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T17:54:34Z","title_canon_sha256":"4e9fb202bb091685bb4534e8cae48e97ea85864c031f6bea6b2d75ce0311ab7e"},"schema_version":"1.0","source":{"id":"2102.04980","kind":"arxiv","version":3}},"canonical_sha256":"12ffc9e2fe8d88d3281590d53caeb3b3cd37b5480646f41fb58559b92161f73a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12ffc9e2fe8d88d3281590d53caeb3b3cd37b5480646f41fb58559b92161f73a","first_computed_at":"2026-07-05T03:08:43.959266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:08:43.959266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bXPVv1kGF8JpHIBNz5l+lI11GNS6gtwslr/tY+KLvaUZ2yumixlFDjoW66bXRhFMHvbTxTniGN7LwV23qSB9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:08:43.959698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.04980","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74ace362e93509501031746ef832bb69b41c343f7fc58e7db9f34517d5da9838","sha256:0c3d94c5da7444a0774d085aa1812e6ce2c55bb89a6b53c856a3e3c6243b42e6"],"state_sha256":"f814341ceeedc95bac1c0866b8f4c8c626581df581612029e3d59781960e38bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3iAeCKIgFQAINbMFVaytdIwMU9wSRM18Zp+DhuC3JLjeQ1q6zQSLSkJG08cNolSdfBpegn0JYJFPKMkfY486CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T11:09:35.325200Z","bundle_sha256":"2465254ac5800f3bd759a9e1d25f94b4d68ac6e5707787d0a99408218c6ea3cf"}}