{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YYCTIMDDJCWU4UL4NA6MMZTNPK","short_pith_number":"pith:YYCTIMDD","schema_version":"1.0","canonical_sha256":"c60534306348ad4e517c683cc6666d7a8ea6baae6c8478c95181e111aa1421b7","source":{"kind":"arxiv","id":"2607.09825","version":1},"attestation_state":"computed","paper":{"title":"More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"ADU), Alap Kshirsagar (IIT Delhi, Alexandre Chapin (LIRIS), Jan Peters (TU Darmstadt), Liming Chen (LIRIS), Yi Li (TU Darmstadt)","submitted_at":"2026-07-10T10:35:24Z","abstract_excerpt":"Robotic manipulation policies rely on pre-trained vision models that give either a global scene embedding or a dense patch grid. Both mix task-relevant and task-irrelevant features. Object-centric slot representations are a structured alternative: they group features into a few per-object slots. We test what this structure buys on ManiSkill3 PickCube-v1, with a frozen encoder and a held-out-seed evaluation. Holding the policy, goal token, rendering, and calibration fixed and changing only the encoder, a frozen object-centric SPOT representation (DINO ViT-B/16 + Slot Attention) reaches 55.0$\\pm"},"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":"2607.09825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-10T10:35:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"017ec1af23135d1adb67a18a30ef9b0b625b617b9937b4e729b115a37658d0b0","abstract_canon_sha256":"33bcc7ecf0ff31b7942b28be30aa97d7af43ba07a10037ca02ca3ad80fa10622"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:37.816815Z","signature_b64":"pw+mNx1Nrnn3hIqbTBegmbAYHN0yhCzdeIotE7cfVtJiG9TUcg3vXjgftBNBMzwJbwPSRgCBlwJXXNh33kN6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c60534306348ad4e517c683cc6666d7a8ea6baae6c8478c95181e111aa1421b7","last_reissued_at":"2026-07-14T00:18:37.815918Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:37.815918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"ADU), Alap Kshirsagar (IIT Delhi, Alexandre Chapin (LIRIS), Jan Peters (TU Darmstadt), Liming Chen (LIRIS), Yi Li (TU Darmstadt)","submitted_at":"2026-07-10T10:35:24Z","abstract_excerpt":"Robotic manipulation policies rely on pre-trained vision models that give either a global scene embedding or a dense patch grid. Both mix task-relevant and task-irrelevant features. Object-centric slot representations are a structured alternative: they group features into a few per-object slots. We test what this structure buys on ManiSkill3 PickCube-v1, with a frozen encoder and a held-out-seed evaluation. Holding the policy, goal token, rendering, and calibration fixed and changing only the encoder, a frozen object-centric SPOT representation (DINO ViT-B/16 + Slot Attention) reaches 55.0$\\pm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09825","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/2607.09825/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":"2607.09825","created_at":"2026-07-14T00:18:37.816377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09825v1","created_at":"2026-07-14T00:18:37.816377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09825","created_at":"2026-07-14T00:18:37.816377+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYCTIMDDJCWU","created_at":"2026-07-14T00:18:37.816377+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYCTIMDDJCWU4UL4","created_at":"2026-07-14T00:18:37.816377+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYCTIMDD","created_at":"2026-07-14T00:18:37.816377+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/YYCTIMDDJCWU4UL4NA6MMZTNPK","json":"https://pith.science/pith/YYCTIMDDJCWU4UL4NA6MMZTNPK.json","graph_json":"https://pith.science/api/pith-number/YYCTIMDDJCWU4UL4NA6MMZTNPK/graph.json","events_json":"https://pith.science/api/pith-number/YYCTIMDDJCWU4UL4NA6MMZTNPK/events.json","paper":"https://pith.science/paper/YYCTIMDD"},"agent_actions":{"view_html":"https://pith.science/pith/YYCTIMDDJCWU4UL4NA6MMZTNPK","download_json":"https://pith.science/pith/YYCTIMDDJCWU4UL4NA6MMZTNPK.json","view_paper":"https://pith.science/paper/YYCTIMDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09825&json=true","fetch_graph":"https://pith.science/api/pith-number/YYCTIMDDJCWU4UL4NA6MMZTNPK/graph.json","fetch_events":"https://pith.science/api/pith-number/YYCTIMDDJCWU4UL4NA6MMZTNPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYCTIMDDJCWU4UL4NA6MMZTNPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYCTIMDDJCWU4UL4NA6MMZTNPK/action/storage_attestation","attest_author":"https://pith.science/pith/YYCTIMDDJCWU4UL4NA6MMZTNPK/action/author_attestation","sign_citation":"https://pith.science/pith/YYCTIMDDJCWU4UL4NA6MMZTNPK/action/citation_signature","submit_replication":"https://pith.science/pith/YYCTIMDDJCWU4UL4NA6MMZTNPK/action/replication_record"}},"created_at":"2026-07-14T00:18:37.816377+00:00","updated_at":"2026-07-14T00:18:37.816377+00:00"}