{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZEHNRAT5PYI2CJNDGHVU6FEXMV","short_pith_number":"pith:ZEHNRAT5","schema_version":"1.0","canonical_sha256":"c90ed8827d7e11a125a331eb4f1497656aa35351afcab3b0617ef547368b71ec","source":{"kind":"arxiv","id":"2209.14860","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Gap to Real-World Object-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Bernhard Sch\\\"olkopf, Carl-Johann Simon-Gabriel, Dominik Zietlow, Francesco Locatello, Max Horn, Maximilian Seitzer, Thomas Brox, Tianjun Xiao, Tong He, Zheng Zhang","submitted_at":"2022-09-29T15:24:47Z","abstract_excerpt":"Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover objects. In this work, we overcome this limitation by showing that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric re"},"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":"2209.14860","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T15:24:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"87cf6146c73fe33fe8322943a6d69ad5533890b9d2684f0ed987b79c610d6f54","abstract_canon_sha256":"6e94e60aaae07d2bbcbb5815362b68e38d8c5d6d7d53c6e66ded0f323316dbff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:39.451950Z","signature_b64":"X7tjj0yWVUHBvUo/LuXNnl7V8TiCB5U+KDPzsDDb1kmN/Ns9lqMsXY1FNVCinhCx5Oqu17hLyXtYEWrRyBegDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c90ed8827d7e11a125a331eb4f1497656aa35351afcab3b0617ef547368b71ec","last_reissued_at":"2026-07-05T05:48:39.451473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:39.451473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap to Real-World Object-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Bernhard Sch\\\"olkopf, Carl-Johann Simon-Gabriel, Dominik Zietlow, Francesco Locatello, Max Horn, Maximilian Seitzer, Thomas Brox, Tianjun Xiao, Tong He, Zheng Zhang","submitted_at":"2022-09-29T15:24:47Z","abstract_excerpt":"Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover objects. In this work, we overcome this limitation by showing that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14860","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/2209.14860/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":"2209.14860","created_at":"2026-07-05T05:48:39.451532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.14860v2","created_at":"2026-07-05T05:48:39.451532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14860","created_at":"2026-07-05T05:48:39.451532+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEHNRAT5PYI2","created_at":"2026-07-05T05:48:39.451532+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEHNRAT5PYI2CJND","created_at":"2026-07-05T05:48:39.451532+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEHNRAT5","created_at":"2026-07-05T05:48:39.451532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13714","citing_title":"TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12601","citing_title":"Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00620","citing_title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03976","citing_title":"Formalizing the Binding Problem","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27696","citing_title":"Structure over Pixels: Learning Variable-Length Visual Programs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11870","citing_title":"Information theoretic underpinning of self-supervised learning by clustering","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09045","citing_title":"Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07099","citing_title":"InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17876","citing_title":"OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV","json":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV.json","graph_json":"https://pith.science/api/pith-number/ZEHNRAT5PYI2CJNDGHVU6FEXMV/graph.json","events_json":"https://pith.science/api/pith-number/ZEHNRAT5PYI2CJNDGHVU6FEXMV/events.json","paper":"https://pith.science/paper/ZEHNRAT5"},"agent_actions":{"view_html":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV","download_json":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV.json","view_paper":"https://pith.science/paper/ZEHNRAT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.14860&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEHNRAT5PYI2CJNDGHVU6FEXMV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEHNRAT5PYI2CJNDGHVU6FEXMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV/action/storage_attestation","attest_author":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV/action/author_attestation","sign_citation":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV/action/citation_signature","submit_replication":"https://pith.science/pith/ZEHNRAT5PYI2CJNDGHVU6FEXMV/action/replication_record"}},"created_at":"2026-07-05T05:48:39.451532+00:00","updated_at":"2026-07-05T05:48:39.451532+00:00"}