{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KI6RXX2F32NWPY4SS6A37YU7R6","short_pith_number":"pith:KI6RXX2F","schema_version":"1.0","canonical_sha256":"523d1bdf45de9b67e3929781bfe29f8fa08c651a9996f26ab01fe4abf6309b29","source":{"kind":"arxiv","id":"2109.07991","version":3},"attestation_state":"computed","paper":{"title":"ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jiajun Wu, Li Fei-Fei, Ruohan Gao, Shivani Mall, Yen-Yu Chang","submitted_at":"2021-09-16T14:00:59Z","abstract_excerpt":"Multisensory object-centric perception, reasoning, and interaction have been a key research topic in recent years. However, the progress in these directions is limited by the small set of objects available -- synthetic objects are not realistic enough and are mostly centered around geometry, while real object datasets such as YCB are often practically challenging and unstable to acquire due to international shipping, inventory, and financial cost. We present ObjectFolder, a dataset of 100 virtualized objects that addresses both challenges with two key innovations. First, ObjectFolder encodes t"},"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":"2109.07991","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-16T14:00:59Z","cross_cats_sorted":["cs.CV","cs.GR","cs.LG"],"title_canon_sha256":"4fa42f866149514d9c01c4f230cc75eb09b1ade2b3e3ec3d21e90f7149865c3d","abstract_canon_sha256":"3c5ce046199215f62792083a59743e6ee841d7f8c8ad02b642e72955a0ca8645"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:52.180591Z","signature_b64":"QEIsMCjcQ4Yp9SlA6SsgSh+juG2ny7DG2Towyc1bNHa8dfglVbm7CYv42rPjtrXWj6qGELsHc+SVn+mTP32iBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"523d1bdf45de9b67e3929781bfe29f8fa08c651a9996f26ab01fe4abf6309b29","last_reissued_at":"2026-07-05T03:29:52.180101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:52.180101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jiajun Wu, Li Fei-Fei, Ruohan Gao, Shivani Mall, Yen-Yu Chang","submitted_at":"2021-09-16T14:00:59Z","abstract_excerpt":"Multisensory object-centric perception, reasoning, and interaction have been a key research topic in recent years. However, the progress in these directions is limited by the small set of objects available -- synthetic objects are not realistic enough and are mostly centered around geometry, while real object datasets such as YCB are often practically challenging and unstable to acquire due to international shipping, inventory, and financial cost. We present ObjectFolder, a dataset of 100 virtualized objects that addresses both challenges with two key innovations. First, ObjectFolder encodes t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07991","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/2109.07991/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":"2109.07991","created_at":"2026-07-05T03:29:52.180166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.07991v3","created_at":"2026-07-05T03:29:52.180166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07991","created_at":"2026-07-05T03:29:52.180166+00:00"},{"alias_kind":"pith_short_12","alias_value":"KI6RXX2F32NW","created_at":"2026-07-05T03:29:52.180166+00:00"},{"alias_kind":"pith_short_16","alias_value":"KI6RXX2F32NWPY4S","created_at":"2026-07-05T03:29:52.180166+00:00"},{"alias_kind":"pith_short_8","alias_value":"KI6RXX2F","created_at":"2026-07-05T03:29:52.180166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25886","citing_title":"A 3D-Printable Dataset for Fair Testing and Comparisons of Tactile Sensors","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12069","citing_title":"Tac-DINO: Learning Vision-Tactile Features with Patch Alignment","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17336","citing_title":"Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6","json":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6.json","graph_json":"https://pith.science/api/pith-number/KI6RXX2F32NWPY4SS6A37YU7R6/graph.json","events_json":"https://pith.science/api/pith-number/KI6RXX2F32NWPY4SS6A37YU7R6/events.json","paper":"https://pith.science/paper/KI6RXX2F"},"agent_actions":{"view_html":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6","download_json":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6.json","view_paper":"https://pith.science/paper/KI6RXX2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.07991&json=true","fetch_graph":"https://pith.science/api/pith-number/KI6RXX2F32NWPY4SS6A37YU7R6/graph.json","fetch_events":"https://pith.science/api/pith-number/KI6RXX2F32NWPY4SS6A37YU7R6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6/action/storage_attestation","attest_author":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6/action/author_attestation","sign_citation":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6/action/citation_signature","submit_replication":"https://pith.science/pith/KI6RXX2F32NWPY4SS6A37YU7R6/action/replication_record"}},"created_at":"2026-07-05T03:29:52.180166+00:00","updated_at":"2026-07-05T03:29:52.180166+00:00"}