{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HH3D5PO2W7HTS5BLWLWOVFTXPC","short_pith_number":"pith:HH3D5PO2","canonical_record":{"source":{"id":"2210.04613","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T13:34:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6350582046452862da10f900a1557920316fb1ceead9945f7abb3a25eb63eb27","abstract_canon_sha256":"6bcec05b9d05823e40a994d782570d6c76b37e4c8cecd4b4db28e8cf0d6da332"},"schema_version":"1.0"},"canonical_sha256":"39f63ebddab7cf39742bb2ecea96777883aa343bc489a3591b34bf80c7507dcd","source":{"kind":"arxiv","id":"2210.04613","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04613","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04613v2","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04613","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"pith_short_12","alias_value":"HH3D5PO2W7HT","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"pith_short_16","alias_value":"HH3D5PO2W7HTS5BL","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"pith_short_8","alias_value":"HH3D5PO2","created_at":"2026-07-05T05:48:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HH3D5PO2W7HTS5BLWLWOVFTXPC","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04613","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T13:34:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6350582046452862da10f900a1557920316fb1ceead9945f7abb3a25eb63eb27","abstract_canon_sha256":"6bcec05b9d05823e40a994d782570d6c76b37e4c8cecd4b4db28e8cf0d6da332"},"schema_version":"1.0"},"canonical_sha256":"39f63ebddab7cf39742bb2ecea96777883aa343bc489a3591b34bf80c7507dcd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:25.711347Z","signature_b64":"V4rHS4FOpTFD7fVYFBRGsOgvTID7567DcT3oJl4xGbwiGpJbCGkgR4z6MSNHx8dlYlnFZoRTdmgbzvyAPMNZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f63ebddab7cf39742bb2ecea96777883aa343bc489a3591b34bf80c7507dcd","last_reissued_at":"2026-07-05T05:48:25.710918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:25.710918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04613","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:48:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aun4czro7G0SjghjpAwfPD49Xjrppqtjj7atZDCzgBTucskD/KYRgm0NNJdCyRCttoEe4+0Uysf8Qm1o+blyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:45:58.623782Z"},"content_sha256":"1ccd18b1dc131d228665b10e5f8e3daa525a5114fd9bd85fa02bc917aa766e53","schema_version":"1.0","event_id":"sha256:1ccd18b1dc131d228665b10e5f8e3daa525a5114fd9bd85fa02bc917aa766e53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HH3D5PO2W7HTS5BLWLWOVFTXPC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Georgios Tziafas, Hamidreza Kasaei, Songsong Xiong","submitted_at":"2022-10-03T13:34:11Z","abstract_excerpt":"Robots operating in human-centered environments, such as retail stores, restaurants, and households, are often required to distinguish between similar objects in different contexts with a high degree of accuracy. However, fine-grained object recognition remains a challenge in robotics due to the high intra-category and low inter-category dissimilarities. In addition, the limited number of fine-grained 3D datasets poses a significant problem in addressing this issue effectively. In this paper, we propose a hybrid multi-modal Vision Transformer (ViT) and Convolutional Neural Networks (CNN) appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04613","kind":"arxiv","version":2},"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/2210.04613/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":"2026-07-05T05:48:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4wPSguWdQdhg27tfhPJU9GezttYCFx0oxBxTHhpZDViaGobWOlYHQWdLijXxuu1Hrv+GHbH5TgzFyhfX9s9BBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:45:58.624162Z"},"content_sha256":"ecd35bdcdf4f04107b08e8f151febe9273caa8567e7b8b9270b7ddfa935e6ee2","schema_version":"1.0","event_id":"sha256:ecd35bdcdf4f04107b08e8f151febe9273caa8567e7b8b9270b7ddfa935e6ee2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HH3D5PO2W7HTS5BLWLWOVFTXPC/bundle.json","state_url":"https://pith.science/pith/HH3D5PO2W7HTS5BLWLWOVFTXPC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HH3D5PO2W7HTS5BLWLWOVFTXPC/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":"2026-07-07T03:45:58Z","links":{"resolver":"https://pith.science/pith/HH3D5PO2W7HTS5BLWLWOVFTXPC","bundle":"https://pith.science/pith/HH3D5PO2W7HTS5BLWLWOVFTXPC/bundle.json","state":"https://pith.science/pith/HH3D5PO2W7HTS5BLWLWOVFTXPC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HH3D5PO2W7HTS5BLWLWOVFTXPC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HH3D5PO2W7HTS5BLWLWOVFTXPC","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":"6bcec05b9d05823e40a994d782570d6c76b37e4c8cecd4b4db28e8cf0d6da332","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T13:34:11Z","title_canon_sha256":"6350582046452862da10f900a1557920316fb1ceead9945f7abb3a25eb63eb27"},"schema_version":"1.0","source":{"id":"2210.04613","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04613","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04613v2","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04613","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"pith_short_12","alias_value":"HH3D5PO2W7HT","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"pith_short_16","alias_value":"HH3D5PO2W7HTS5BL","created_at":"2026-07-05T05:48:25Z"},{"alias_kind":"pith_short_8","alias_value":"HH3D5PO2","created_at":"2026-07-05T05:48:25Z"}],"graph_snapshots":[{"event_id":"sha256:ecd35bdcdf4f04107b08e8f151febe9273caa8567e7b8b9270b7ddfa935e6ee2","target":"graph","created_at":"2026-07-05T05:48:25Z","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/2210.04613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robots operating in human-centered environments, such as retail stores, restaurants, and households, are often required to distinguish between similar objects in different contexts with a high degree of accuracy. However, fine-grained object recognition remains a challenge in robotics due to the high intra-category and low inter-category dissimilarities. In addition, the limited number of fine-grained 3D datasets poses a significant problem in addressing this issue effectively. In this paper, we propose a hybrid multi-modal Vision Transformer (ViT) and Convolutional Neural Networks (CNN) appro","authors_text":"Georgios Tziafas, Hamidreza Kasaei, Songsong Xiong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T13:34:11Z","title":"Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04613","kind":"arxiv","version":2},"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":"sha256:1ccd18b1dc131d228665b10e5f8e3daa525a5114fd9bd85fa02bc917aa766e53","target":"record","created_at":"2026-07-05T05:48:25Z","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":"6bcec05b9d05823e40a994d782570d6c76b37e4c8cecd4b4db28e8cf0d6da332","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T13:34:11Z","title_canon_sha256":"6350582046452862da10f900a1557920316fb1ceead9945f7abb3a25eb63eb27"},"schema_version":"1.0","source":{"id":"2210.04613","kind":"arxiv","version":2}},"canonical_sha256":"39f63ebddab7cf39742bb2ecea96777883aa343bc489a3591b34bf80c7507dcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39f63ebddab7cf39742bb2ecea96777883aa343bc489a3591b34bf80c7507dcd","first_computed_at":"2026-07-05T05:48:25.710918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:25.710918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V4rHS4FOpTFD7fVYFBRGsOgvTID7567DcT3oJl4xGbwiGpJbCGkgR4z6MSNHx8dlYlnFZoRTdmgbzvyAPMNZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:25.711347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04613","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ccd18b1dc131d228665b10e5f8e3daa525a5114fd9bd85fa02bc917aa766e53","sha256:ecd35bdcdf4f04107b08e8f151febe9273caa8567e7b8b9270b7ddfa935e6ee2"],"state_sha256":"29cf7b89c385978b747702cb6e38cab6b99ddd73e48c992c33e54848b559575f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/PimKICavo5oNFUsc1AUPmpfJRvceNrM5V3KbSWG7h3njswba3cHntxNmZ7q1moNROSz6hY1a5etPCEbptr2Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:45:58.626104Z","bundle_sha256":"4805c19ac0d9b4170c0eb03d0e2023c987c9a2c15923d10bc8b6f4fb4905c822"}}