{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MWCHDSP7L4NNLRITAVODMVMF4Y","short_pith_number":"pith:MWCHDSP7","canonical_record":{"source":{"id":"2402.15933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-24T23:31:34Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"a73902d98b1ab6397cf383e9835392d59a1eb929095ed8bb8ddd78a5d51a599a","abstract_canon_sha256":"530ce70191d9f4ebef0f707de880df92e11d02a381dce4ede328712a52fceb52"},"schema_version":"1.0"},"canonical_sha256":"658471c9ff5f1ad5c513055c365585e619c5096a393630e0428edfae425bc041","source":{"kind":"arxiv","id":"2402.15933","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15933","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15933v1","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15933","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"MWCHDSP7L4NN","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"pith_short_16","alias_value":"MWCHDSP7L4NNLRIT","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"pith_short_8","alias_value":"MWCHDSP7","created_at":"2026-07-05T07:48:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MWCHDSP7L4NNLRITAVODMVMF4Y","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-24T23:31:34Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"a73902d98b1ab6397cf383e9835392d59a1eb929095ed8bb8ddd78a5d51a599a","abstract_canon_sha256":"530ce70191d9f4ebef0f707de880df92e11d02a381dce4ede328712a52fceb52"},"schema_version":"1.0"},"canonical_sha256":"658471c9ff5f1ad5c513055c365585e619c5096a393630e0428edfae425bc041","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:59.954994Z","signature_b64":"B6t4uD+IotHm7Nxb5kO2CcroO6Av39OygkwoxPFWbzu+GvkohdsYNobs27fXyUYASJpKB5gtICWYgsL6PuevDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"658471c9ff5f1ad5c513055c365585e619c5096a393630e0428edfae425bc041","last_reissued_at":"2026-07-05T07:48:59.954526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:59.954526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15933","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":"2026-07-05T07:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkoNuJKaFMMhX1XIZXcZHjVoNbL5SCwK5v4Sv5LlCsp69u+KcmR5KNSBlDoqheC8eyZZSyKGHxsqEnp2jn6wCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:02:34.470767Z"},"content_sha256":"2dcff3eab106f98f967b8a63323af0621506f7034da4eced430f210a027af27a","schema_version":"1.0","event_id":"sha256:2dcff3eab106f98f967b8a63323af0621506f7034da4eced430f210a027af27a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MWCHDSP7L4NNLRITAVODMVMF4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Wentao Mo, Yang Liu","submitted_at":"2024-02-24T23:31:34Z","abstract_excerpt":"In 3D Visual Question Answering (3D VQA), the scarcity of fully annotated data and limited visual content diversity hampers the generalization to novel scenes and 3D concepts (e.g., only around 800 scenes are utilized in ScanQA and SQA dataset). Current approaches resort supplement 3D reasoning with 2D information. However, these methods face challenges: either they use top-down 2D views that introduce overly complex and sometimes question-irrelevant visual clues, or they rely on globally aggregated scene/image-level representations from 2D VLMs, losing the fine-grained vision-language correla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15933","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/2402.15933/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":"2026-07-05T07:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cu2l6l4awuqFfaXhLIOz02YhBxaXHB3g/cay8UwsIeJoCN5y68YAHYmvzVY52dHq8ZyC1OzSuSgDGZ8WX6v5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:02:34.471497Z"},"content_sha256":"efd8191e9aaaf7284af55016ceb74c70e48d8c1d5351924fc2b6105e8f4f1ae4","schema_version":"1.0","event_id":"sha256:efd8191e9aaaf7284af55016ceb74c70e48d8c1d5351924fc2b6105e8f4f1ae4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWCHDSP7L4NNLRITAVODMVMF4Y/bundle.json","state_url":"https://pith.science/pith/MWCHDSP7L4NNLRITAVODMVMF4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWCHDSP7L4NNLRITAVODMVMF4Y/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":"2026-08-14T02:02:34Z","links":{"resolver":"https://pith.science/pith/MWCHDSP7L4NNLRITAVODMVMF4Y","bundle":"https://pith.science/pith/MWCHDSP7L4NNLRITAVODMVMF4Y/bundle.json","state":"https://pith.science/pith/MWCHDSP7L4NNLRITAVODMVMF4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWCHDSP7L4NNLRITAVODMVMF4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MWCHDSP7L4NNLRITAVODMVMF4Y","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":"530ce70191d9f4ebef0f707de880df92e11d02a381dce4ede328712a52fceb52","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-24T23:31:34Z","title_canon_sha256":"a73902d98b1ab6397cf383e9835392d59a1eb929095ed8bb8ddd78a5d51a599a"},"schema_version":"1.0","source":{"id":"2402.15933","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15933","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15933v1","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15933","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"MWCHDSP7L4NN","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"pith_short_16","alias_value":"MWCHDSP7L4NNLRIT","created_at":"2026-07-05T07:48:59Z"},{"alias_kind":"pith_short_8","alias_value":"MWCHDSP7","created_at":"2026-07-05T07:48:59Z"}],"graph_snapshots":[{"event_id":"sha256:efd8191e9aaaf7284af55016ceb74c70e48d8c1d5351924fc2b6105e8f4f1ae4","target":"graph","created_at":"2026-07-05T07:48:59Z","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/2402.15933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In 3D Visual Question Answering (3D VQA), the scarcity of fully annotated data and limited visual content diversity hampers the generalization to novel scenes and 3D concepts (e.g., only around 800 scenes are utilized in ScanQA and SQA dataset). Current approaches resort supplement 3D reasoning with 2D information. However, these methods face challenges: either they use top-down 2D views that introduce overly complex and sometimes question-irrelevant visual clues, or they rely on globally aggregated scene/image-level representations from 2D VLMs, losing the fine-grained vision-language correla","authors_text":"Wentao Mo, Yang Liu","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-24T23:31:34Z","title":"Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15933","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":"sha256:2dcff3eab106f98f967b8a63323af0621506f7034da4eced430f210a027af27a","target":"record","created_at":"2026-07-05T07:48:59Z","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":"530ce70191d9f4ebef0f707de880df92e11d02a381dce4ede328712a52fceb52","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-24T23:31:34Z","title_canon_sha256":"a73902d98b1ab6397cf383e9835392d59a1eb929095ed8bb8ddd78a5d51a599a"},"schema_version":"1.0","source":{"id":"2402.15933","kind":"arxiv","version":1}},"canonical_sha256":"658471c9ff5f1ad5c513055c365585e619c5096a393630e0428edfae425bc041","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"658471c9ff5f1ad5c513055c365585e619c5096a393630e0428edfae425bc041","first_computed_at":"2026-07-05T07:48:59.954526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:59.954526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B6t4uD+IotHm7Nxb5kO2CcroO6Av39OygkwoxPFWbzu+GvkohdsYNobs27fXyUYASJpKB5gtICWYgsL6PuevDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:59.954994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15933","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dcff3eab106f98f967b8a63323af0621506f7034da4eced430f210a027af27a","sha256:efd8191e9aaaf7284af55016ceb74c70e48d8c1d5351924fc2b6105e8f4f1ae4"],"state_sha256":"cf81a5a262a2cfd86aa020452c7a125434d77b6bf7571ae6df624f7de7d1d1a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBBnS17MuDQjv6L6fgcw6e5pEvFv7AjQbT+XtKzXM8bsocU83IQFQKqLXUDllOfBbxGkFugLxN33K3sZ3DiXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T02:02:34.478407Z","bundle_sha256":"8c2ec5b144400b6a85fde24ce5cb720b731496e1fe71b5ab4d8fcfceb59a2ea8"}}