{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CVYQO7DKJWSR6GBCDOK5L27NX6","short_pith_number":"pith:CVYQO7DK","canonical_record":{"source":{"id":"2210.10486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-19T11:50:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc3c6a7a52f4e35d01f724118dd5ba5d5a1500a226b71282d4e8089ff6fa6417","abstract_canon_sha256":"494e48d855cc955c6f082d04adae51e0fb005e9886320e5b4be4de81d929d3dc"},"schema_version":"1.0"},"canonical_sha256":"1571077c6a4da51f18221b95d5ebedbf92e99a0ddaa95194e8054c60d33f4087","source":{"kind":"arxiv","id":"2210.10486","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.10486","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.10486v1","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10486","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"CVYQO7DKJWSR","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"CVYQO7DKJWSR6GBC","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"CVYQO7DK","created_at":"2026-07-05T05:08:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CVYQO7DKJWSR6GBCDOK5L27NX6","target":"record","payload":{"canonical_record":{"source":{"id":"2210.10486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-19T11:50:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc3c6a7a52f4e35d01f724118dd5ba5d5a1500a226b71282d4e8089ff6fa6417","abstract_canon_sha256":"494e48d855cc955c6f082d04adae51e0fb005e9886320e5b4be4de81d929d3dc"},"schema_version":"1.0"},"canonical_sha256":"1571077c6a4da51f18221b95d5ebedbf92e99a0ddaa95194e8054c60d33f4087","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:20.346769Z","signature_b64":"fW45eqXPwZfno2UCoZLVd4QKSBF53g0FOu0pqyXrCvn0qdlM0nO/9M88XuyWqRx9lMW8PmOIwp0teT/Zo3tMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1571077c6a4da51f18221b95d5ebedbf92e99a0ddaa95194e8054c60d33f4087","last_reissued_at":"2026-07-05T05:08:20.346309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:20.346309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.10486","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":"2026-07-05T05:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++pt8uymIYmn7HuIFWiaXc+3tocko2eFXFLD/j5RhbaJRJjPmzK9xf8B4YW4z2z2aiwD4Crs5xOiaFWyHRdIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:28:37.770627Z"},"content_sha256":"e09b6f5a29fa663b8502654239d49b8f0c4c9c656c9151cbd3635f12a681a3a9","schema_version":"1.0","event_id":"sha256:e09b6f5a29fa663b8502654239d49b8f0c4c9c656c9151cbd3635f12a681a3a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CVYQO7DKJWSR6GBCDOK5L27NX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhra Chaudhuri, Anjan Dutta, Massimiliano Mancini, Yanbei Chen, Zeynep Akata","submitted_at":"2022-10-19T11:50:14Z","abstract_excerpt":"Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information. As instances from different modalities can often provide complementary information describing the underlying concept, we propose a cross-attention framework for Vision Transformers (XModalViT) that fuses modality-specific information instead of discarding them. Our framework first maps paired datapoints from the individual photo and sketch modalities to fused representations that unify information from both modalities. We then decouple the input sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10486","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/2210.10486/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":"2026-07-05T05:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8PtM8gAwE2/1zNeTo72fvnzxsr5EDcvk5aYH428XVhj42MOTxYdSPF6EPQoEgwPaOULPtdMGL8DuMRVLRrpbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:28:37.771132Z"},"content_sha256":"53d012478204e15ed5916be8dd92be4c2308852e1a1441a071ba8e871811d6bd","schema_version":"1.0","event_id":"sha256:53d012478204e15ed5916be8dd92be4c2308852e1a1441a071ba8e871811d6bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CVYQO7DKJWSR6GBCDOK5L27NX6/bundle.json","state_url":"https://pith.science/pith/CVYQO7DKJWSR6GBCDOK5L27NX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CVYQO7DKJWSR6GBCDOK5L27NX6/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":"2026-08-18T22:28:37Z","links":{"resolver":"https://pith.science/pith/CVYQO7DKJWSR6GBCDOK5L27NX6","bundle":"https://pith.science/pith/CVYQO7DKJWSR6GBCDOK5L27NX6/bundle.json","state":"https://pith.science/pith/CVYQO7DKJWSR6GBCDOK5L27NX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CVYQO7DKJWSR6GBCDOK5L27NX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CVYQO7DKJWSR6GBCDOK5L27NX6","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":"494e48d855cc955c6f082d04adae51e0fb005e9886320e5b4be4de81d929d3dc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-19T11:50:14Z","title_canon_sha256":"bc3c6a7a52f4e35d01f724118dd5ba5d5a1500a226b71282d4e8089ff6fa6417"},"schema_version":"1.0","source":{"id":"2210.10486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.10486","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.10486v1","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10486","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"CVYQO7DKJWSR","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"CVYQO7DKJWSR6GBC","created_at":"2026-07-05T05:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"CVYQO7DK","created_at":"2026-07-05T05:08:20Z"}],"graph_snapshots":[{"event_id":"sha256:53d012478204e15ed5916be8dd92be4c2308852e1a1441a071ba8e871811d6bd","target":"graph","created_at":"2026-07-05T05:08:20Z","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/2210.10486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information. As instances from different modalities can often provide complementary information describing the underlying concept, we propose a cross-attention framework for Vision Transformers (XModalViT) that fuses modality-specific information instead of discarding them. Our framework first maps paired datapoints from the individual photo and sketch modalities to fused representations that unify information from both modalities. We then decouple the input sp","authors_text":"Abhra Chaudhuri, Anjan Dutta, Massimiliano Mancini, Yanbei Chen, Zeynep Akata","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-19T11:50:14Z","title":"Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10486","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:e09b6f5a29fa663b8502654239d49b8f0c4c9c656c9151cbd3635f12a681a3a9","target":"record","created_at":"2026-07-05T05:08:20Z","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":"494e48d855cc955c6f082d04adae51e0fb005e9886320e5b4be4de81d929d3dc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-19T11:50:14Z","title_canon_sha256":"bc3c6a7a52f4e35d01f724118dd5ba5d5a1500a226b71282d4e8089ff6fa6417"},"schema_version":"1.0","source":{"id":"2210.10486","kind":"arxiv","version":1}},"canonical_sha256":"1571077c6a4da51f18221b95d5ebedbf92e99a0ddaa95194e8054c60d33f4087","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1571077c6a4da51f18221b95d5ebedbf92e99a0ddaa95194e8054c60d33f4087","first_computed_at":"2026-07-05T05:08:20.346309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:20.346309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fW45eqXPwZfno2UCoZLVd4QKSBF53g0FOu0pqyXrCvn0qdlM0nO/9M88XuyWqRx9lMW8PmOIwp0teT/Zo3tMAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:20.346769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.10486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e09b6f5a29fa663b8502654239d49b8f0c4c9c656c9151cbd3635f12a681a3a9","sha256:53d012478204e15ed5916be8dd92be4c2308852e1a1441a071ba8e871811d6bd"],"state_sha256":"52662cf6d63056e18e57e241f26d250e4d629dfb56152bb9a8b9e4e59e7c4bee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VYoxSbF+WMJk1juc6dYkuPlS3lstSaRTO1Xrcq/mGrfAkq1p92zVnkUbvahF6yqXBsKilrfYnlKzEENt2+9PBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:28:37.775754Z","bundle_sha256":"65e471f14412d5ba8a26d70ce5b1380ecc3106ccf85cb52f2f1017813403e6cb"}}