{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z3WM4TXHTVCRWVVEYF3CJXCIRT","short_pith_number":"pith:Z3WM4TXH","schema_version":"1.0","canonical_sha256":"ceecce4ee79d451b56a4c17624dc488cd0e9a9c0e570deef006fa01d3efa8871","source":{"kind":"arxiv","id":"2404.13474","version":1},"attestation_state":"computed","paper":{"title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Dinesh Jayaraman, Jianing Qian, Junyao Shi, Yecheng Jason Ma","submitted_at":"2024-04-20T21:51:15Z","abstract_excerpt":"There have recently been large advances both in pre-training visual representations for robotic control and segmenting unknown category objects in general images. To leverage these for improved robot learning, we propose $\\textbf{POCR}$, a new framework for building pre-trained object-centric representations for robotic control. Building on theories of \"what-where\" representations in psychology and computer vision, we use segmentations from a pre-trained model to stably locate across timesteps, various entities in the scene, capturing \"where\" information. To each such segmented entity, we appl"},"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":"2404.13474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-04-20T21:51:15Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"db971cd4e69fc9d2c8324d1e1443f9ad8bdab5b7452f10f501064f28e18796c8","abstract_canon_sha256":"4139ab6c4b23ae79296071d8b1e6b78f74667c589469ea3369bb13e7940d564c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:32.645830Z","signature_b64":"/CGr5RNJbWtD0aeZGapKR4IQQ6CjNsUDnDiMzGVPFQ8IdU6Y/bemF58pIvOuftRYVFd7EbUKOriC1wfW1e3BDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceecce4ee79d451b56a4c17624dc488cd0e9a9c0e570deef006fa01d3efa8871","last_reissued_at":"2026-07-05T08:10:32.645377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:32.645377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Dinesh Jayaraman, Jianing Qian, Junyao Shi, Yecheng Jason Ma","submitted_at":"2024-04-20T21:51:15Z","abstract_excerpt":"There have recently been large advances both in pre-training visual representations for robotic control and segmenting unknown category objects in general images. To leverage these for improved robot learning, we propose $\\textbf{POCR}$, a new framework for building pre-trained object-centric representations for robotic control. Building on theories of \"what-where\" representations in psychology and computer vision, we use segmentations from a pre-trained model to stably locate across timesteps, various entities in the scene, capturing \"where\" information. To each such segmented entity, we appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13474","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/2404.13474/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":"2404.13474","created_at":"2026-07-05T08:10:32.645432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13474v1","created_at":"2026-07-05T08:10:32.645432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13474","created_at":"2026-07-05T08:10:32.645432+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3WM4TXHTVCR","created_at":"2026-07-05T08:10:32.645432+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3WM4TXHTVCRWVVE","created_at":"2026-07-05T08:10:32.645432+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3WM4TXH","created_at":"2026-07-05T08:10:32.645432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT","json":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT.json","graph_json":"https://pith.science/api/pith-number/Z3WM4TXHTVCRWVVEYF3CJXCIRT/graph.json","events_json":"https://pith.science/api/pith-number/Z3WM4TXHTVCRWVVEYF3CJXCIRT/events.json","paper":"https://pith.science/paper/Z3WM4TXH"},"agent_actions":{"view_html":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT","download_json":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT.json","view_paper":"https://pith.science/paper/Z3WM4TXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13474&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3WM4TXHTVCRWVVEYF3CJXCIRT/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3WM4TXHTVCRWVVEYF3CJXCIRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT/action/storage_attestation","attest_author":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT/action/author_attestation","sign_citation":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT/action/citation_signature","submit_replication":"https://pith.science/pith/Z3WM4TXHTVCRWVVEYF3CJXCIRT/action/replication_record"}},"created_at":"2026-07-05T08:10:32.645432+00:00","updated_at":"2026-07-05T08:10:32.645432+00:00"}