{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EEKLRVOVVI2UNQTJFHCR3EFMIP","short_pith_number":"pith:EEKLRVOV","schema_version":"1.0","canonical_sha256":"2114b8d5d5aa3546c26929c51d90ac43c9ba28a3b7b822bd940cdf448207d699","source":{"kind":"arxiv","id":"2302.04973","version":2},"attestation_state":"computed","paper":{"title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aravindh Mahendran, Gamaleldin F. Elsayed, Mehdi S. M. Sajjadi, Ondrej Biza, Sjoerd van Steenkiste, Thomas Kipf","submitted_at":"2023-02-09T23:25:28Z","abstract_excerpt":"Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress in this direction. However, they typically fall short at adequately capturing spatial symmetries present in the visual world, which leads to sample inefficiency, such as when entangling object appearance and pose. In this paper, we present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We incorpor"},"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":"2302.04973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-09T23:25:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ea20bf925a6bafae2f09b6a95bc8bc24402280e891fe31536f9f168bdc3b2af8","abstract_canon_sha256":"cae2e3acce64d61b8352dc05ce88dc797cc2fcb71c372ff7a85d8e6c00706563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:18.721684Z","signature_b64":"mgiU70e4/JAS+U31iev9RQF04Ouim5riPGJrr+5iqJJMoCfCfnqQQ0iQwICNrVyibJ97XCXRdle+c/TDXyOpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2114b8d5d5aa3546c26929c51d90ac43c9ba28a3b7b822bd940cdf448207d699","last_reissued_at":"2026-07-05T06:33:18.721165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:18.721165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aravindh Mahendran, Gamaleldin F. Elsayed, Mehdi S. M. Sajjadi, Ondrej Biza, Sjoerd van Steenkiste, Thomas Kipf","submitted_at":"2023-02-09T23:25:28Z","abstract_excerpt":"Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress in this direction. However, they typically fall short at adequately capturing spatial symmetries present in the visual world, which leads to sample inefficiency, such as when entangling object appearance and pose. In this paper, we present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We incorpor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04973","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/2302.04973/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":"2302.04973","created_at":"2026-07-05T06:33:18.721233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04973v2","created_at":"2026-07-05T06:33:18.721233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04973","created_at":"2026-07-05T06:33:18.721233+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEKLRVOVVI2U","created_at":"2026-07-05T06:33:18.721233+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEKLRVOVVI2UNQTJ","created_at":"2026-07-05T06:33:18.721233+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEKLRVOV","created_at":"2026-07-05T06:33:18.721233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12601","citing_title":"Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP","json":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP.json","graph_json":"https://pith.science/api/pith-number/EEKLRVOVVI2UNQTJFHCR3EFMIP/graph.json","events_json":"https://pith.science/api/pith-number/EEKLRVOVVI2UNQTJFHCR3EFMIP/events.json","paper":"https://pith.science/paper/EEKLRVOV"},"agent_actions":{"view_html":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP","download_json":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP.json","view_paper":"https://pith.science/paper/EEKLRVOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04973&json=true","fetch_graph":"https://pith.science/api/pith-number/EEKLRVOVVI2UNQTJFHCR3EFMIP/graph.json","fetch_events":"https://pith.science/api/pith-number/EEKLRVOVVI2UNQTJFHCR3EFMIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP/action/storage_attestation","attest_author":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP/action/author_attestation","sign_citation":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP/action/citation_signature","submit_replication":"https://pith.science/pith/EEKLRVOVVI2UNQTJFHCR3EFMIP/action/replication_record"}},"created_at":"2026-07-05T06:33:18.721233+00:00","updated_at":"2026-07-05T06:33:18.721233+00:00"}