{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B7HT7HSLMISVWD7I2ARZWJOUNQ","short_pith_number":"pith:B7HT7HSL","canonical_record":{"source":{"id":"2406.11579","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T14:16:12Z","cross_cats_sorted":[],"title_canon_sha256":"dfacb9c56848037e7d825da6acfcb7ea0f0323f0fb002a9bcd9408aaeffac7a9","abstract_canon_sha256":"58d8ea07157cea1685c77cadd6ccb37d37c4b54c878376eede091d6fe7003b48"},"schema_version":"1.0"},"canonical_sha256":"0fcf3f9e4b62255b0fe8d0239b25d46c3d51bd68d164684baed5e425a7c0c891","source":{"kind":"arxiv","id":"2406.11579","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11579","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11579v3","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11579","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"pith_short_12","alias_value":"B7HT7HSLMISV","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"pith_short_16","alias_value":"B7HT7HSLMISVWD7I","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"pith_short_8","alias_value":"B7HT7HSL","created_at":"2026-07-05T10:35:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B7HT7HSLMISVWD7I2ARZWJOUNQ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11579","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T14:16:12Z","cross_cats_sorted":[],"title_canon_sha256":"dfacb9c56848037e7d825da6acfcb7ea0f0323f0fb002a9bcd9408aaeffac7a9","abstract_canon_sha256":"58d8ea07157cea1685c77cadd6ccb37d37c4b54c878376eede091d6fe7003b48"},"schema_version":"1.0"},"canonical_sha256":"0fcf3f9e4b62255b0fe8d0239b25d46c3d51bd68d164684baed5e425a7c0c891","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:33.712906Z","signature_b64":"pIfmCOXpDiQKyxm8Z1pX61mAFPsULQ39NhaMm9rbQomYLXRkzLZ/2kRuBmiJvGXLLqgo+vExeV6DOqAys8VlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fcf3f9e4b62255b0fe8d0239b25d46c3d51bd68d164684baed5e425a7c0c891","last_reissued_at":"2026-07-05T10:35:33.712371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:33.712371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11579","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":"2026-07-05T10:35:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BMyIXHK1ZU47ZYDaGZOLM4GXOYw4uRVychi3TW0ONz0vcZelAs4Ydne8WZKXmN2Z484Db/DLCcWzbZLPLykJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:39:18.356694Z"},"content_sha256":"d86153df438c750eb7a871c726049e970168fc645804a62af204c112f3df99c2","schema_version":"1.0","event_id":"sha256:d86153df438c750eb7a871c726049e970168fc645804a62af204c112f3df99c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B7HT7HSLMISVWD7I2ARZWJOUNQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angel X. Chang, Han-Hung Lee, Yiming Zhang","submitted_at":"2024-06-17T14:16:12Z","abstract_excerpt":"We introduce Duoduo CLIP, a model for 3D representation learning that learns shape encodings from multi-view images instead of point clouds. The choice of multi-view images allows us to leverage 2D priors from off-the-shelf CLIP models to facilitate fine-tuning with 3D data. Our approach not only shows better generalization compared to existing point cloud methods, but also reduces GPU requirements and training time. In addition, the model is modified with cross-view attention to leverage information across multiple frames of the object which further boosts performance. Notably, our model is p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11579","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/2406.11579/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":"2026-07-05T10:35:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e6EaqJOnR9jTJNCSXcV0x471/aX6zpxcAvMAvjc7itSCcCBdwGP4PRFOf4c2qb/kolErjRPBOPcjPCwfEjwZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:39:18.357229Z"},"content_sha256":"0f05d14b5a90a8d9d08bc812a266939960bbc7147cea2e85ecf4b347f5e46ad3","schema_version":"1.0","event_id":"sha256:0f05d14b5a90a8d9d08bc812a266939960bbc7147cea2e85ecf4b347f5e46ad3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B7HT7HSLMISVWD7I2ARZWJOUNQ/bundle.json","state_url":"https://pith.science/pith/B7HT7HSLMISVWD7I2ARZWJOUNQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B7HT7HSLMISVWD7I2ARZWJOUNQ/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":"2026-08-04T20:39:18Z","links":{"resolver":"https://pith.science/pith/B7HT7HSLMISVWD7I2ARZWJOUNQ","bundle":"https://pith.science/pith/B7HT7HSLMISVWD7I2ARZWJOUNQ/bundle.json","state":"https://pith.science/pith/B7HT7HSLMISVWD7I2ARZWJOUNQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B7HT7HSLMISVWD7I2ARZWJOUNQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B7HT7HSLMISVWD7I2ARZWJOUNQ","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":"58d8ea07157cea1685c77cadd6ccb37d37c4b54c878376eede091d6fe7003b48","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T14:16:12Z","title_canon_sha256":"dfacb9c56848037e7d825da6acfcb7ea0f0323f0fb002a9bcd9408aaeffac7a9"},"schema_version":"1.0","source":{"id":"2406.11579","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11579","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11579v3","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11579","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"pith_short_12","alias_value":"B7HT7HSLMISV","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"pith_short_16","alias_value":"B7HT7HSLMISVWD7I","created_at":"2026-07-05T10:35:33Z"},{"alias_kind":"pith_short_8","alias_value":"B7HT7HSL","created_at":"2026-07-05T10:35:33Z"}],"graph_snapshots":[{"event_id":"sha256:0f05d14b5a90a8d9d08bc812a266939960bbc7147cea2e85ecf4b347f5e46ad3","target":"graph","created_at":"2026-07-05T10:35:33Z","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/2406.11579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Duoduo CLIP, a model for 3D representation learning that learns shape encodings from multi-view images instead of point clouds. The choice of multi-view images allows us to leverage 2D priors from off-the-shelf CLIP models to facilitate fine-tuning with 3D data. Our approach not only shows better generalization compared to existing point cloud methods, but also reduces GPU requirements and training time. In addition, the model is modified with cross-view attention to leverage information across multiple frames of the object which further boosts performance. Notably, our model is p","authors_text":"Angel X. Chang, Han-Hung Lee, Yiming Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T14:16:12Z","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11579","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:d86153df438c750eb7a871c726049e970168fc645804a62af204c112f3df99c2","target":"record","created_at":"2026-07-05T10:35:33Z","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":"58d8ea07157cea1685c77cadd6ccb37d37c4b54c878376eede091d6fe7003b48","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T14:16:12Z","title_canon_sha256":"dfacb9c56848037e7d825da6acfcb7ea0f0323f0fb002a9bcd9408aaeffac7a9"},"schema_version":"1.0","source":{"id":"2406.11579","kind":"arxiv","version":3}},"canonical_sha256":"0fcf3f9e4b62255b0fe8d0239b25d46c3d51bd68d164684baed5e425a7c0c891","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fcf3f9e4b62255b0fe8d0239b25d46c3d51bd68d164684baed5e425a7c0c891","first_computed_at":"2026-07-05T10:35:33.712371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:33.712371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pIfmCOXpDiQKyxm8Z1pX61mAFPsULQ39NhaMm9rbQomYLXRkzLZ/2kRuBmiJvGXLLqgo+vExeV6DOqAys8VlCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:33.712906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11579","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d86153df438c750eb7a871c726049e970168fc645804a62af204c112f3df99c2","sha256:0f05d14b5a90a8d9d08bc812a266939960bbc7147cea2e85ecf4b347f5e46ad3"],"state_sha256":"50685802b1c63e52078d26fb3c2d5f14f52c87fc33eca858af20a5961f698608"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EXshMNLFV9M4EJIRrXvQo1vPm/kXH4RYzgQIwDpWJ9WmAlc8K0nn6g7bRstzjI41WN0GQq/vSfLUj5pDlCAIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:39:18.362258Z","bundle_sha256":"22e62a1656acb8341213b0814448b574bdfa1d2066213a9ea26fab50eb1459b3"}}