{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XNOP3YCP2MUFOIJ3JAFTNMFJDF","short_pith_number":"pith:XNOP3YCP","schema_version":"1.0","canonical_sha256":"bb5cfde04fd32857213b480b36b0a91964e89e2150817d64d1f16f36c58ec297","source":{"kind":"arxiv","id":"2306.00956","version":1},"attestation_state":"computed","paper":{"title":"The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.HC","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hao Li, Jeannette Bohg, Jiajun Wu, Li Fei-Fei, Ruohan Gao, Tanmay Agarwal, Yiming Dou, Yunzhu Li","submitted_at":"2023-06-01T17:51:22Z","abstract_excerpt":"We introduce the ObjectFolder Benchmark, a benchmark suite of 10 tasks for multisensory object-centric learning, centered around object recognition, reconstruction, and manipulation with sight, sound, and touch. We also introduce the ObjectFolder Real dataset, including the multisensory measurements for 100 real-world household objects, building upon a newly designed pipeline for collecting the 3D meshes, videos, impact sounds, and tactile readings of real-world objects. We conduct systematic benchmarking on both the 1,000 multisensory neural objects from ObjectFolder, and the real multisensor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.00956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T17:51:22Z","cross_cats_sorted":["cs.AI","cs.GR","cs.HC","cs.RO"],"title_canon_sha256":"bc3d438e7a9f06b748519bf813614fd376d41b91dbcb6ff351fbfd123baf67ee","abstract_canon_sha256":"a74d8e73450c6dfeeabd0458fd513adfb5479085f00b85d4a77c4dba548ce601"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:33.756579Z","signature_b64":"oVuCHkCeRNoLyjuHRm4n1QyNBTDwoGjC5V71zqwQhUL/8D+h3nyqhTZvTb0Cq1Yh/+SWumSmQLfW+urkgLPsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb5cfde04fd32857213b480b36b0a91964e89e2150817d64d1f16f36c58ec297","last_reissued_at":"2026-07-05T06:16:33.755960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:33.755960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.HC","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hao Li, Jeannette Bohg, Jiajun Wu, Li Fei-Fei, Ruohan Gao, Tanmay Agarwal, Yiming Dou, Yunzhu Li","submitted_at":"2023-06-01T17:51:22Z","abstract_excerpt":"We introduce the ObjectFolder Benchmark, a benchmark suite of 10 tasks for multisensory object-centric learning, centered around object recognition, reconstruction, and manipulation with sight, sound, and touch. We also introduce the ObjectFolder Real dataset, including the multisensory measurements for 100 real-world household objects, building upon a newly designed pipeline for collecting the 3D meshes, videos, impact sounds, and tactile readings of real-world objects. We conduct systematic benchmarking on both the 1,000 multisensory neural objects from ObjectFolder, and the real multisensor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00956","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/2306.00956/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.00956","created_at":"2026-07-05T06:16:33.756034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00956v1","created_at":"2026-07-05T06:16:33.756034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00956","created_at":"2026-07-05T06:16:33.756034+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNOP3YCP2MUF","created_at":"2026-07-05T06:16:33.756034+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNOP3YCP2MUFOIJ3","created_at":"2026-07-05T06:16:33.756034+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNOP3YCP","created_at":"2026-07-05T06:16:33.756034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.14573","citing_title":"Modality Selection and Skill Segmentation via Cross-Modality Attention","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF","json":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF.json","graph_json":"https://pith.science/api/pith-number/XNOP3YCP2MUFOIJ3JAFTNMFJDF/graph.json","events_json":"https://pith.science/api/pith-number/XNOP3YCP2MUFOIJ3JAFTNMFJDF/events.json","paper":"https://pith.science/paper/XNOP3YCP"},"agent_actions":{"view_html":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF","download_json":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF.json","view_paper":"https://pith.science/paper/XNOP3YCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00956&json=true","fetch_graph":"https://pith.science/api/pith-number/XNOP3YCP2MUFOIJ3JAFTNMFJDF/graph.json","fetch_events":"https://pith.science/api/pith-number/XNOP3YCP2MUFOIJ3JAFTNMFJDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF/action/storage_attestation","attest_author":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF/action/author_attestation","sign_citation":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF/action/citation_signature","submit_replication":"https://pith.science/pith/XNOP3YCP2MUFOIJ3JAFTNMFJDF/action/replication_record"}},"created_at":"2026-07-05T06:16:33.756034+00:00","updated_at":"2026-07-05T06:16:33.756034+00:00"}