{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OCLMTGQGFGWF7ROYG5YE5T5ASQ","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":"1db09dbfbc5e230895c7b62dadc88f338ae2855de4fa13b2db23ba92d12205ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T00:15:40Z","title_canon_sha256":"fe5cf3c9350246ad49a819be6db55cdb56170569722f70ff54d5943763c69e35"},"schema_version":"1.0","source":{"id":"2310.16856","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16856","created_at":"2026-07-05T07:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16856v1","created_at":"2026-07-05T07:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16856","created_at":"2026-07-05T07:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"OCLMTGQGFGWF","created_at":"2026-07-05T07:05:15Z"},{"alias_kind":"pith_short_16","alias_value":"OCLMTGQGFGWF7ROY","created_at":"2026-07-05T07:05:15Z"},{"alias_kind":"pith_short_8","alias_value":"OCLMTGQG","created_at":"2026-07-05T07:05:15Z"}],"graph_snapshots":[{"event_id":"sha256:cb7799dd1e1dac6638d5339bd74d8e984f98fe174412026931b409e5dec67c18","target":"graph","created_at":"2026-07-05T07:05:15Z","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/2310.16856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Object Re-Identification (ReID) is pivotal in computer vision, witnessing an escalating demand for adept multimodal representation learning. Current models, although promising, reveal scalability limitations with increasing modalities as they rely heavily on late fusion, which postpones the integration of specific modality insights. Addressing this, we introduce the \\textbf{Gradual Fusion Transformer (GraFT)} for multimodal ReID. At its core, GraFT employs learnable fusion tokens that guide self-attention across encoders, adeptly capturing both modality-specific and object-specific features. F","authors_text":"Daniel Cummings, Eva Schiller, Haoli Yin, Jiayao Li (Emily), Luke McDermott","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T00:15:40Z","title":"GraFT: Gradual Fusion Transformer for Multimodal Re-Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16856","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":"sha256:598554ba581e229a15a098f83310be4782ede975e2298df009350a4cb8c07437","target":"record","created_at":"2026-07-05T07:05:15Z","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":"1db09dbfbc5e230895c7b62dadc88f338ae2855de4fa13b2db23ba92d12205ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T00:15:40Z","title_canon_sha256":"fe5cf3c9350246ad49a819be6db55cdb56170569722f70ff54d5943763c69e35"},"schema_version":"1.0","source":{"id":"2310.16856","kind":"arxiv","version":1}},"canonical_sha256":"7096c99a0629ac5fc5d837704ecfa094063582348e953f3c4dfd51e0b596d01d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7096c99a0629ac5fc5d837704ecfa094063582348e953f3c4dfd51e0b596d01d","first_computed_at":"2026-07-05T07:05:15.141078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:15.141078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"29NAWIyNgoa3EYxOTBPyyTexlvlNd+fTIVYs4dqj3BDXKhqlv9HoS89AW70L5h98+gRf6oTlQlffcFPHTV6TBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:15.141585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16856","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:598554ba581e229a15a098f83310be4782ede975e2298df009350a4cb8c07437","sha256:cb7799dd1e1dac6638d5339bd74d8e984f98fe174412026931b409e5dec67c18"],"state_sha256":"dd4773217d8c32e15c94e253a821914f7fbbd297b5039dd24e2ea8f29a3d52f8"}