{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:X3O2BC4S7WRD5CA4RNQKUMP2VC","short_pith_number":"pith:X3O2BC4S","schema_version":"1.0","canonical_sha256":"bedda08b92fda23e881c8b60aa31faa8bda8751f8ace83b82ba1ae92c079259d","source":{"kind":"arxiv","id":"2205.06333","version":2},"attestation_state":"computed","paper":{"title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ayzaan Wahid, Corey Lynch, Debidatta Dwibedi, Jeannette Bohg, Jonathan Tompson, Negin Heravi, Pete Florence, Pierre Sermanet, Travis Armstrong","submitted_at":"2022-05-12T19:48:11Z","abstract_excerpt":"Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the current methodologies learn task specific representations that do not necessarily transfer well to other tasks. Furthermore, representations learned by supervised methods require large labeled datasets for each task that are expensive to collect in the real world. Using self-supervised learning to obtain representations from unlabeled data can mitigate this"},"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":"2205.06333","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-12T19:48:11Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"e61c9746f30e54c6f6efe8cdaaaf3977264cb28243125ebf8bbfc7fd2383acce","abstract_canon_sha256":"c1af3623201dcefba98252acf766543084d8eb0ce4ad6250465ef36064a59c3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:06.033935Z","signature_b64":"+U5lNRxri876133ClBWcP8O9+Yo9izuGweU91Rr20P4HI4duQKaMO6vtn5ayl3zrgEefnzJVLoXcXP8p5Lp7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bedda08b92fda23e881c8b60aa31faa8bda8751f8ace83b82ba1ae92c079259d","last_reissued_at":"2026-07-05T05:50:06.033522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:06.033522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ayzaan Wahid, Corey Lynch, Debidatta Dwibedi, Jeannette Bohg, Jonathan Tompson, Negin Heravi, Pete Florence, Pierre Sermanet, Travis Armstrong","submitted_at":"2022-05-12T19:48:11Z","abstract_excerpt":"Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the current methodologies learn task specific representations that do not necessarily transfer well to other tasks. Furthermore, representations learned by supervised methods require large labeled datasets for each task that are expensive to collect in the real world. Using self-supervised learning to obtain representations from unlabeled data can mitigate this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06333","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/2205.06333/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":"2205.06333","created_at":"2026-07-05T05:50:06.033582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.06333v2","created_at":"2026-07-05T05:50:06.033582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06333","created_at":"2026-07-05T05:50:06.033582+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3O2BC4S7WRD","created_at":"2026-07-05T05:50:06.033582+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3O2BC4S7WRD5CA4","created_at":"2026-07-05T05:50:06.033582+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3O2BC4S","created_at":"2026-07-05T05:50:06.033582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.06754","citing_title":"SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC","json":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC.json","graph_json":"https://pith.science/api/pith-number/X3O2BC4S7WRD5CA4RNQKUMP2VC/graph.json","events_json":"https://pith.science/api/pith-number/X3O2BC4S7WRD5CA4RNQKUMP2VC/events.json","paper":"https://pith.science/paper/X3O2BC4S"},"agent_actions":{"view_html":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC","download_json":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC.json","view_paper":"https://pith.science/paper/X3O2BC4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.06333&json=true","fetch_graph":"https://pith.science/api/pith-number/X3O2BC4S7WRD5CA4RNQKUMP2VC/graph.json","fetch_events":"https://pith.science/api/pith-number/X3O2BC4S7WRD5CA4RNQKUMP2VC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC/action/storage_attestation","attest_author":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC/action/author_attestation","sign_citation":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC/action/citation_signature","submit_replication":"https://pith.science/pith/X3O2BC4S7WRD5CA4RNQKUMP2VC/action/replication_record"}},"created_at":"2026-07-05T05:50:06.033582+00:00","updated_at":"2026-07-05T05:50:06.033582+00:00"}