{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MQZDYKHUZ2DTGBIB3UCM6WFM43","short_pith_number":"pith:MQZDYKHU","schema_version":"1.0","canonical_sha256":"64323c28f4ce87330501dd04cf58ace6da69dbbfdb26f309090ecd3b010f3f22","source":{"kind":"arxiv","id":"2408.09162","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Object-Centric Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Aniket Didolkar, Anirudh Goyal, Georg Martius, Maximilian Seitzer, Mike Mozer, Yoshua Bengio","submitted_at":"2024-08-17T10:37:07Z","abstract_excerpt":"The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we stud"},"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":"2408.09162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-17T10:37:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"609ec5747d2e646843a0969d56b6498400cbce4d5c05ae97fe7e48a278fced83","abstract_canon_sha256":"91b02fc5d7604c136750af3ed7b1e89c25c2468581d580d37bdc10b1e12e7b65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:29.058307Z","signature_b64":"gcaSI7Ar3pn27wYiDpHX8a4GBjfiZG5HljpnTVmEV4tJ+lE4r0cAEp6TlekcJM6e51yFk1dXZkl/tEOHAYSEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64323c28f4ce87330501dd04cf58ace6da69dbbfdb26f309090ecd3b010f3f22","last_reissued_at":"2026-07-05T08:56:29.057934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:29.057934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Object-Centric Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Aniket Didolkar, Anirudh Goyal, Georg Martius, Maximilian Seitzer, Mike Mozer, Yoshua Bengio","submitted_at":"2024-08-17T10:37:07Z","abstract_excerpt":"The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09162","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/2408.09162/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":"2408.09162","created_at":"2026-07-05T08:56:29.057992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09162v1","created_at":"2026-07-05T08:56:29.057992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09162","created_at":"2026-07-05T08:56:29.057992+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQZDYKHUZ2DT","created_at":"2026-07-05T08:56:29.057992+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQZDYKHUZ2DTGBIB","created_at":"2026-07-05T08:56:29.057992+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQZDYKHU","created_at":"2026-07-05T08:56:29.057992+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":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43","json":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43.json","graph_json":"https://pith.science/api/pith-number/MQZDYKHUZ2DTGBIB3UCM6WFM43/graph.json","events_json":"https://pith.science/api/pith-number/MQZDYKHUZ2DTGBIB3UCM6WFM43/events.json","paper":"https://pith.science/paper/MQZDYKHU"},"agent_actions":{"view_html":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43","download_json":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43.json","view_paper":"https://pith.science/paper/MQZDYKHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09162&json=true","fetch_graph":"https://pith.science/api/pith-number/MQZDYKHUZ2DTGBIB3UCM6WFM43/graph.json","fetch_events":"https://pith.science/api/pith-number/MQZDYKHUZ2DTGBIB3UCM6WFM43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43/action/storage_attestation","attest_author":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43/action/author_attestation","sign_citation":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43/action/citation_signature","submit_replication":"https://pith.science/pith/MQZDYKHUZ2DTGBIB3UCM6WFM43/action/replication_record"}},"created_at":"2026-07-05T08:56:29.057992+00:00","updated_at":"2026-07-05T08:56:29.057992+00:00"}