{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BRAOG3NVQNVDFLL5OIEGX4TVII","short_pith_number":"pith:BRAOG3NV","schema_version":"1.0","canonical_sha256":"0c40e36db5836a32ad7d72086bf275421fd4a2a3a6b8365e39b7cbbc6d17be28","source":{"kind":"arxiv","id":"2405.15916","version":1},"attestation_state":"computed","paper":{"title":"Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Anastasios Panagopoulos, Dinesh Jayaraman, Jianing Qian","submitted_at":"2024-05-24T20:20:15Z","abstract_excerpt":"Generic re-usable pre-trained image representation encoders have become a standard component of methods for many computer vision tasks. As visual representations for robots however, their utility has been limited, leading to a recent wave of efforts to pre-train robotics-specific image encoders that are better suited to robotic tasks than their generic counterparts. We propose Scene Objects From Transformers, abbreviated as SOFT, a wrapper around pre-trained vision transformer (PVT) models that bridges this gap without any further training. Rather than construct representations out of only the"},"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":"2405.15916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T20:20:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"63c7e8fd9ee715477e18f075813c5ec0381733e677fefe7c3045c05ed9342b7a","abstract_canon_sha256":"a9b3a7c32dac7ed87ed42388f11685b8a20e56244d84295d7a5ed624ffffc00c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:58.405522Z","signature_b64":"VoWaI6aZ8b9C7h6phygVPPDmsGBELOV/TlHua6D4SGvWXevQi/nv+rZq4z5HPX54+DGPzPvA0UP6jU1m0ZOMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c40e36db5836a32ad7d72086bf275421fd4a2a3a6b8365e39b7cbbc6d17be28","last_reissued_at":"2026-07-05T08:22:58.405052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:58.405052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Anastasios Panagopoulos, Dinesh Jayaraman, Jianing Qian","submitted_at":"2024-05-24T20:20:15Z","abstract_excerpt":"Generic re-usable pre-trained image representation encoders have become a standard component of methods for many computer vision tasks. As visual representations for robots however, their utility has been limited, leading to a recent wave of efforts to pre-train robotics-specific image encoders that are better suited to robotic tasks than their generic counterparts. We propose Scene Objects From Transformers, abbreviated as SOFT, a wrapper around pre-trained vision transformer (PVT) models that bridges this gap without any further training. Rather than construct representations out of only the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15916","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/2405.15916/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":"2405.15916","created_at":"2026-07-05T08:22:58.405107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15916v1","created_at":"2026-07-05T08:22:58.405107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15916","created_at":"2026-07-05T08:22:58.405107+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRAOG3NVQNVD","created_at":"2026-07-05T08:22:58.405107+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRAOG3NVQNVDFLL5","created_at":"2026-07-05T08:22:58.405107+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRAOG3NV","created_at":"2026-07-05T08:22:58.405107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19408","citing_title":"Is an object-centric representation beneficial for robotic manipulation ?","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII","json":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII.json","graph_json":"https://pith.science/api/pith-number/BRAOG3NVQNVDFLL5OIEGX4TVII/graph.json","events_json":"https://pith.science/api/pith-number/BRAOG3NVQNVDFLL5OIEGX4TVII/events.json","paper":"https://pith.science/paper/BRAOG3NV"},"agent_actions":{"view_html":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII","download_json":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII.json","view_paper":"https://pith.science/paper/BRAOG3NV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15916&json=true","fetch_graph":"https://pith.science/api/pith-number/BRAOG3NVQNVDFLL5OIEGX4TVII/graph.json","fetch_events":"https://pith.science/api/pith-number/BRAOG3NVQNVDFLL5OIEGX4TVII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII/action/storage_attestation","attest_author":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII/action/author_attestation","sign_citation":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII/action/citation_signature","submit_replication":"https://pith.science/pith/BRAOG3NVQNVDFLL5OIEGX4TVII/action/replication_record"}},"created_at":"2026-07-05T08:22:58.405107+00:00","updated_at":"2026-07-05T08:22:58.405107+00:00"}