{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:65ZNJHXBKAEA2YESAVR3UU5ON2","short_pith_number":"pith:65ZNJHXB","canonical_record":{"source":{"id":"2504.09518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T11:10:47Z","cross_cats_sorted":[],"title_canon_sha256":"927dece04fb9195006673ad7275417a280aaff3cb53ba7f64fecd572ae1597b9","abstract_canon_sha256":"0740863111df0172d880b27ab4c06e0c2b86b4180d1c23f86f1d1dc68b94f507"},"schema_version":"1.0"},"canonical_sha256":"f772d49ee150080d60920563ba53ae6e870ee96e838a29f502687c8b28e1c9d4","source":{"kind":"arxiv","id":"2504.09518","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09518","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09518v1","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09518","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"65ZNJHXBKAEA","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"65ZNJHXBKAEA2YES","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"65ZNJHXB","created_at":"2026-07-05T10:48:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:65ZNJHXBKAEA2YESAVR3UU5ON2","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T11:10:47Z","cross_cats_sorted":[],"title_canon_sha256":"927dece04fb9195006673ad7275417a280aaff3cb53ba7f64fecd572ae1597b9","abstract_canon_sha256":"0740863111df0172d880b27ab4c06e0c2b86b4180d1c23f86f1d1dc68b94f507"},"schema_version":"1.0"},"canonical_sha256":"f772d49ee150080d60920563ba53ae6e870ee96e838a29f502687c8b28e1c9d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:38.942198Z","signature_b64":"VimiUyS1dMu7VEUWAj9QsjQqPenqAS7kCe0m+D1jxc2GmYfLsQvqzhgkQ8NxGj2bOOQqB3i6Zglwvctosvn8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f772d49ee150080d60920563ba53ae6e870ee96e838a29f502687c8b28e1c9d4","last_reissued_at":"2026-07-05T10:48:38.941735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:38.941735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09518","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":"2026-07-05T10:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lsfyFqsk2kTGy4s6sIdnR1pQBGFEFgPqILFl7jOtTUyXFIi5JD/HEYWcR6TFp/V8D6nH1Cn7N419Nv9odm4+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:27:08.896595Z"},"content_sha256":"1bc61ed2e77507271f1cf8e7c92d034404ccf909bc16c70eb83def61d4e754ce","schema_version":"1.0","event_id":"sha256:1bc61ed2e77507271f1cf8e7c92d034404ccf909bc16c70eb83def61d4e754ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:65ZNJHXBKAEA2YESAVR3UU5ON2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"3D CoCa: Contrastive Learners are 3D Captioners","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Ting Huang, Yemin Wang, Zeyu Zhang","submitted_at":"2025-04-13T11:10:47Z","abstract_excerpt":"3D captioning, which aims to describe the content of 3D scenes in natural language, remains highly challenging due to the inherent sparsity of point clouds and weak cross-modal alignment in existing methods. To address these challenges, we propose 3D CoCa, a novel unified framework that seamlessly combines contrastive vision-language learning with 3D caption generation in a single architecture. Our approach leverages a frozen CLIP vision-language backbone to provide rich semantic priors, a spatially-aware 3D scene encoder to capture geometric context, and a multi-modal decoder to generate desc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09518","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/2504.09518/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":"2026-07-05T10:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XsuX3ySeDZyeuTNpnXKeqSEKmS9JwNwyAWVPWjFXp2+6yM3MGpArR7idrBQKUzZai5DTb3MhzB7AXUtyk3b9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:27:08.897223Z"},"content_sha256":"e7a4efc0e92b58f77f8bbf2bfec0949a920811d9519e2258daa305c47d99aa00","schema_version":"1.0","event_id":"sha256:e7a4efc0e92b58f77f8bbf2bfec0949a920811d9519e2258daa305c47d99aa00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/65ZNJHXBKAEA2YESAVR3UU5ON2/bundle.json","state_url":"https://pith.science/pith/65ZNJHXBKAEA2YESAVR3UU5ON2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/65ZNJHXBKAEA2YESAVR3UU5ON2/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":"2026-08-09T12:27:08Z","links":{"resolver":"https://pith.science/pith/65ZNJHXBKAEA2YESAVR3UU5ON2","bundle":"https://pith.science/pith/65ZNJHXBKAEA2YESAVR3UU5ON2/bundle.json","state":"https://pith.science/pith/65ZNJHXBKAEA2YESAVR3UU5ON2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/65ZNJHXBKAEA2YESAVR3UU5ON2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:65ZNJHXBKAEA2YESAVR3UU5ON2","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":"0740863111df0172d880b27ab4c06e0c2b86b4180d1c23f86f1d1dc68b94f507","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T11:10:47Z","title_canon_sha256":"927dece04fb9195006673ad7275417a280aaff3cb53ba7f64fecd572ae1597b9"},"schema_version":"1.0","source":{"id":"2504.09518","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09518","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09518v1","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09518","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"65ZNJHXBKAEA","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"65ZNJHXBKAEA2YES","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"65ZNJHXB","created_at":"2026-07-05T10:48:38Z"}],"graph_snapshots":[{"event_id":"sha256:e7a4efc0e92b58f77f8bbf2bfec0949a920811d9519e2258daa305c47d99aa00","target":"graph","created_at":"2026-07-05T10:48:38Z","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/2504.09518/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D captioning, which aims to describe the content of 3D scenes in natural language, remains highly challenging due to the inherent sparsity of point clouds and weak cross-modal alignment in existing methods. To address these challenges, we propose 3D CoCa, a novel unified framework that seamlessly combines contrastive vision-language learning with 3D caption generation in a single architecture. Our approach leverages a frozen CLIP vision-language backbone to provide rich semantic priors, a spatially-aware 3D scene encoder to capture geometric context, and a multi-modal decoder to generate desc","authors_text":"Hao Tang, Ting Huang, Yemin Wang, Zeyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T11:10:47Z","title":"3D CoCa: Contrastive Learners are 3D Captioners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09518","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":"sha256:1bc61ed2e77507271f1cf8e7c92d034404ccf909bc16c70eb83def61d4e754ce","target":"record","created_at":"2026-07-05T10:48:38Z","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":"0740863111df0172d880b27ab4c06e0c2b86b4180d1c23f86f1d1dc68b94f507","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T11:10:47Z","title_canon_sha256":"927dece04fb9195006673ad7275417a280aaff3cb53ba7f64fecd572ae1597b9"},"schema_version":"1.0","source":{"id":"2504.09518","kind":"arxiv","version":1}},"canonical_sha256":"f772d49ee150080d60920563ba53ae6e870ee96e838a29f502687c8b28e1c9d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f772d49ee150080d60920563ba53ae6e870ee96e838a29f502687c8b28e1c9d4","first_computed_at":"2026-07-05T10:48:38.941735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:38.941735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VimiUyS1dMu7VEUWAj9QsjQqPenqAS7kCe0m+D1jxc2GmYfLsQvqzhgkQ8NxGj2bOOQqB3i6Zglwvctosvn8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:38.942198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09518","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bc61ed2e77507271f1cf8e7c92d034404ccf909bc16c70eb83def61d4e754ce","sha256:e7a4efc0e92b58f77f8bbf2bfec0949a920811d9519e2258daa305c47d99aa00"],"state_sha256":"14e6213f57abad4d969c79e0fbc1093f94c88f5b169d4e077e4b3b43fab39646"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fbEm8F58be2MUGVPQzm6li5irwxzmP17gpMLiEFVNjxrJJKnKhUXi4CH8oxcctQ9ig3RYvsxST63GQkpxsLoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:27:08.901461Z","bundle_sha256":"ff4c5614e05a6f19d6ba130b6d32fcd666dfecd549d969778a2a94e7646cc4d2"}}