{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TIBZGJE6URSZZNGLJ25B5GYO4N","short_pith_number":"pith:TIBZGJE6","schema_version":"1.0","canonical_sha256":"9a0393249ea4659cb4cb4eba1e9b0ee37434ca30a4cc2b542f2a95b1a58b9d0a","source":{"kind":"arxiv","id":"2311.00926","version":1},"attestation_state":"computed","paper":{"title":"M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Adithyavairavan Murali, Arsalan Mousavian, Dieter Fox, Wentao Yuan","submitted_at":"2023-11-02T01:42:52Z","abstract_excerpt":"With the advent of large language models and large-scale robotic datasets, there has been tremendous progress in high-level decision-making for object manipulation. These generic models are able to interpret complex tasks using language commands, but they often have difficulties generalizing to out-of-distribution objects due to the inability of low-level action primitives. In contrast, existing task-specific models excel in low-level manipulation of unknown objects, but only work for a single type of action. To bridge this gap, we present M2T2, a single model that supplies different types of "},"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":"2311.00926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T01:42:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0a2398ec1ef4f6130b2313f5b4d3dcd169a71840e2862ad9e13ea97e60372e99","abstract_canon_sha256":"447b39ee12687d832a6af9c53e7f4907c84f5f41d0b4bd8bbb19406b37c8af87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:17.671445Z","signature_b64":"3XIP0E5OKRVuHe8xbw0rVKkI9WwbsKPoYWtQCRxdhDZogKxlBzuDRvvnfK0UGuvsyvYbI3+BOnmVsRi+hGTTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a0393249ea4659cb4cb4eba1e9b0ee37434ca30a4cc2b542f2a95b1a58b9d0a","last_reissued_at":"2026-07-05T07:08:17.670916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:17.670916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Adithyavairavan Murali, Arsalan Mousavian, Dieter Fox, Wentao Yuan","submitted_at":"2023-11-02T01:42:52Z","abstract_excerpt":"With the advent of large language models and large-scale robotic datasets, there has been tremendous progress in high-level decision-making for object manipulation. These generic models are able to interpret complex tasks using language commands, but they often have difficulties generalizing to out-of-distribution objects due to the inability of low-level action primitives. In contrast, existing task-specific models excel in low-level manipulation of unknown objects, but only work for a single type of action. To bridge this gap, we present M2T2, a single model that supplies different types of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00926","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/2311.00926/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":"2311.00926","created_at":"2026-07-05T07:08:17.670981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00926v1","created_at":"2026-07-05T07:08:17.670981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00926","created_at":"2026-07-05T07:08:17.670981+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIBZGJE6URSZ","created_at":"2026-07-05T07:08:17.670981+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIBZGJE6URSZZNGL","created_at":"2026-07-05T07:08:17.670981+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIBZGJE6","created_at":"2026-07-05T07:08:17.670981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.16857","citing_title":"BOP-ASK: Object-Interaction Reasoning for Vision-Language Models","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N","json":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N.json","graph_json":"https://pith.science/api/pith-number/TIBZGJE6URSZZNGLJ25B5GYO4N/graph.json","events_json":"https://pith.science/api/pith-number/TIBZGJE6URSZZNGLJ25B5GYO4N/events.json","paper":"https://pith.science/paper/TIBZGJE6"},"agent_actions":{"view_html":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N","download_json":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N.json","view_paper":"https://pith.science/paper/TIBZGJE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00926&json=true","fetch_graph":"https://pith.science/api/pith-number/TIBZGJE6URSZZNGLJ25B5GYO4N/graph.json","fetch_events":"https://pith.science/api/pith-number/TIBZGJE6URSZZNGLJ25B5GYO4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N/action/storage_attestation","attest_author":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N/action/author_attestation","sign_citation":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N/action/citation_signature","submit_replication":"https://pith.science/pith/TIBZGJE6URSZZNGLJ25B5GYO4N/action/replication_record"}},"created_at":"2026-07-05T07:08:17.670981+00:00","updated_at":"2026-07-05T07:08:17.670981+00:00"}