{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LEQHTGDPKXGY5RLWYO2UYASHKQ","short_pith_number":"pith:LEQHTGDP","canonical_record":{"source":{"id":"2311.17851","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T17:54:22Z","cross_cats_sorted":[],"title_canon_sha256":"4c27bcfaff091a012484c91c9c8332b564ed5282b1fdcfd50f8b76af24f6253a","abstract_canon_sha256":"3f99d4cdc8249fb0fcae3e0a5015c3ec072152990eb365e6223edea226e27664"},"schema_version":"1.0"},"canonical_sha256":"592079986f55cd8ec576c3b54c0247541b252fdd0569b8c0bb29b17b3b0b27fc","source":{"kind":"arxiv","id":"2311.17851","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17851","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17851v2","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17851","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"LEQHTGDPKXGY","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LEQHTGDPKXGY5RLW","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LEQHTGDP","created_at":"2026-07-05T08:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LEQHTGDPKXGY5RLWYO2UYASHKQ","target":"record","payload":{"canonical_record":{"source":{"id":"2311.17851","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T17:54:22Z","cross_cats_sorted":[],"title_canon_sha256":"4c27bcfaff091a012484c91c9c8332b564ed5282b1fdcfd50f8b76af24f6253a","abstract_canon_sha256":"3f99d4cdc8249fb0fcae3e0a5015c3ec072152990eb365e6223edea226e27664"},"schema_version":"1.0"},"canonical_sha256":"592079986f55cd8ec576c3b54c0247541b252fdd0569b8c0bb29b17b3b0b27fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:33.398793Z","signature_b64":"MqzA/4++6NoupWM1OlUF4RWL5Koos3qLdKtDkDGkrEhk04ibI1U6dTieqEZVl0SnD7uiYA0HukGjWS+EbzY+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"592079986f55cd8ec576c3b54c0247541b252fdd0569b8c0bb29b17b3b0b27fc","last_reissued_at":"2026-07-05T08:32:33.398279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:33.398279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.17851","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":"2026-07-05T08:32:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"URvwbu0oirmNsZOMEK5HVwVcqt9oVs9qvojzXP4oS1UVDrQ/ajcoMcQ0Ig0SuAi/g3jboflMVDLBowm3VWiLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:45:56.975505Z"},"content_sha256":"ac7b1ed9fa2f74724fc9deece6aed2e4fbac247cac0ee627436b067defcf2f7e","schema_version":"1.0","event_id":"sha256:ac7b1ed9fa2f74724fc9deece6aed2e4fbac247cac0ee627436b067defcf2f7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LEQHTGDPKXGY5RLWYO2UYASHKQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging VLM-Based Pipelines to Annotate 3D Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Lerchner, Loic Matthey, Niloy J. Mitra, Rishabh Kabra","submitted_at":"2023-11-29T17:54:22Z","abstract_excerpt":"Pretrained vision language models (VLMs) present an opportunity to caption unlabeled 3D objects at scale. The leading approach to summarize VLM descriptions from different views of an object (Luo et al., 2023) relies on a language model (GPT4) to produce the final output. This text-based aggregation is susceptible to hallucinations as it merges potentially contradictory descriptions. We propose an alternative algorithm to marginalize over factors such as the viewpoint that affect the VLM's response. Instead of merging text-only responses, we utilize the VLM's joint image-text likelihoods. We s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17851","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/2311.17851/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":"2026-07-05T08:32:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kE7X+qY3cbtPgNZn9wRClt2ajVSw23A/abvn7uhHLqXf26JHGQCppTuqHQMjlm49fGS+kxFosOTQirGF75jXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:45:56.976027Z"},"content_sha256":"e05cbdce285659c78b8001a2072fae067e66ccd34d4aa4198d4d92299c9de66f","schema_version":"1.0","event_id":"sha256:e05cbdce285659c78b8001a2072fae067e66ccd34d4aa4198d4d92299c9de66f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LEQHTGDPKXGY5RLWYO2UYASHKQ/bundle.json","state_url":"https://pith.science/pith/LEQHTGDPKXGY5RLWYO2UYASHKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LEQHTGDPKXGY5RLWYO2UYASHKQ/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":"2026-08-18T05:45:56Z","links":{"resolver":"https://pith.science/pith/LEQHTGDPKXGY5RLWYO2UYASHKQ","bundle":"https://pith.science/pith/LEQHTGDPKXGY5RLWYO2UYASHKQ/bundle.json","state":"https://pith.science/pith/LEQHTGDPKXGY5RLWYO2UYASHKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LEQHTGDPKXGY5RLWYO2UYASHKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LEQHTGDPKXGY5RLWYO2UYASHKQ","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":"3f99d4cdc8249fb0fcae3e0a5015c3ec072152990eb365e6223edea226e27664","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T17:54:22Z","title_canon_sha256":"4c27bcfaff091a012484c91c9c8332b564ed5282b1fdcfd50f8b76af24f6253a"},"schema_version":"1.0","source":{"id":"2311.17851","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17851","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17851v2","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17851","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"LEQHTGDPKXGY","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LEQHTGDPKXGY5RLW","created_at":"2026-07-05T08:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LEQHTGDP","created_at":"2026-07-05T08:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:e05cbdce285659c78b8001a2072fae067e66ccd34d4aa4198d4d92299c9de66f","target":"graph","created_at":"2026-07-05T08:32:33Z","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/2311.17851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained vision language models (VLMs) present an opportunity to caption unlabeled 3D objects at scale. The leading approach to summarize VLM descriptions from different views of an object (Luo et al., 2023) relies on a language model (GPT4) to produce the final output. This text-based aggregation is susceptible to hallucinations as it merges potentially contradictory descriptions. We propose an alternative algorithm to marginalize over factors such as the viewpoint that affect the VLM's response. Instead of merging text-only responses, we utilize the VLM's joint image-text likelihoods. We s","authors_text":"Alexander Lerchner, Loic Matthey, Niloy J. Mitra, Rishabh Kabra","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T17:54:22Z","title":"Leveraging VLM-Based Pipelines to Annotate 3D Objects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17851","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:ac7b1ed9fa2f74724fc9deece6aed2e4fbac247cac0ee627436b067defcf2f7e","target":"record","created_at":"2026-07-05T08:32:33Z","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":"3f99d4cdc8249fb0fcae3e0a5015c3ec072152990eb365e6223edea226e27664","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T17:54:22Z","title_canon_sha256":"4c27bcfaff091a012484c91c9c8332b564ed5282b1fdcfd50f8b76af24f6253a"},"schema_version":"1.0","source":{"id":"2311.17851","kind":"arxiv","version":2}},"canonical_sha256":"592079986f55cd8ec576c3b54c0247541b252fdd0569b8c0bb29b17b3b0b27fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"592079986f55cd8ec576c3b54c0247541b252fdd0569b8c0bb29b17b3b0b27fc","first_computed_at":"2026-07-05T08:32:33.398279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:33.398279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MqzA/4++6NoupWM1OlUF4RWL5Koos3qLdKtDkDGkrEhk04ibI1U6dTieqEZVl0SnD7uiYA0HukGjWS+EbzY+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:33.398793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17851","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac7b1ed9fa2f74724fc9deece6aed2e4fbac247cac0ee627436b067defcf2f7e","sha256:e05cbdce285659c78b8001a2072fae067e66ccd34d4aa4198d4d92299c9de66f"],"state_sha256":"35e49278f929765f80992e14156d89dc4352b3a43b5c33f70b803ad257350f0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bVDJ3hc9QmXYlCXtZMujailjPWNSHvQdP26FTYqicooK1o89H/1joNcyPUXCkLDcPXi0Ek6PinRGuLhdDKxDBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T05:45:56.981035Z","bundle_sha256":"3c2eb24ebb0bbd84b2e408ffa65899692a1a219e640ad9ff8fc5e54fd0229ea9"}}