{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VFSTBZURBIWL6WZTMNXPCNQSHE","short_pith_number":"pith:VFSTBZUR","schema_version":"1.0","canonical_sha256":"a96530e6910a2cbf5b33636ef1361239243ccd987ea2f75ccce14519f98f1559","source":{"kind":"arxiv","id":"1910.02384","version":4},"attestation_state":"computed","paper":{"title":"SCALOR: Generative World Models with Scalable Object Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gerard de Melo, Jindong Jiang, Sepehr Janghorbani, Sungjin Ahn","submitted_at":"2019-10-06T06:26:31Z","abstract_excerpt":"Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning. Most of the previous models have been shown to work only on scenes with a few objects. In this paper, we propose SCALOR, a probabilistic generative world model for learning SCALable Object-oriented Representation of a video. With the proposed spatially-parallel attention and proposal-rejection mechanisms, SCALOR can deal with orders of magnitude larger numbers of objects compared to the previous state-of-the-art models. Additionally, we introduce a backgr"},"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":"1910.02384","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-06T06:26:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4da8f49606be20e3e386d1d421493eb5fdf83bb3219fd3c40b7b7ee336fd376d","abstract_canon_sha256":"32f3894fb865588d7ec6fcbe7f1f3c9e900107eb7a9e2ca74aa14e8263183189"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:52.454977Z","signature_b64":"6iDT9FnPHoP+zIhwnE5ahvzfR1/vuwz9t3rEKVmLQghDCtlBjpGettu68QuSH5fvSWbjBvyNB0tkL4xdNs3hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a96530e6910a2cbf5b33636ef1361239243ccd987ea2f75ccce14519f98f1559","last_reissued_at":"2026-07-05T00:45:52.454509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:52.454509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCALOR: Generative World Models with Scalable Object Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gerard de Melo, Jindong Jiang, Sepehr Janghorbani, Sungjin Ahn","submitted_at":"2019-10-06T06:26:31Z","abstract_excerpt":"Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning. Most of the previous models have been shown to work only on scenes with a few objects. In this paper, we propose SCALOR, a probabilistic generative world model for learning SCALable Object-oriented Representation of a video. With the proposed spatially-parallel attention and proposal-rejection mechanisms, SCALOR can deal with orders of magnitude larger numbers of objects compared to the previous state-of-the-art models. Additionally, we introduce a backgr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02384","kind":"arxiv","version":4},"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/1910.02384/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":"1910.02384","created_at":"2026-07-05T00:45:52.454579+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.02384v4","created_at":"2026-07-05T00:45:52.454579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02384","created_at":"2026-07-05T00:45:52.454579+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFSTBZURBIWL","created_at":"2026-07-05T00:45:52.454579+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFSTBZURBIWL6WZT","created_at":"2026-07-05T00:45:52.454579+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFSTBZUR","created_at":"2026-07-05T00:45:52.454579+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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE","json":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE.json","graph_json":"https://pith.science/api/pith-number/VFSTBZURBIWL6WZTMNXPCNQSHE/graph.json","events_json":"https://pith.science/api/pith-number/VFSTBZURBIWL6WZTMNXPCNQSHE/events.json","paper":"https://pith.science/paper/VFSTBZUR"},"agent_actions":{"view_html":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE","download_json":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE.json","view_paper":"https://pith.science/paper/VFSTBZUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.02384&json=true","fetch_graph":"https://pith.science/api/pith-number/VFSTBZURBIWL6WZTMNXPCNQSHE/graph.json","fetch_events":"https://pith.science/api/pith-number/VFSTBZURBIWL6WZTMNXPCNQSHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE/action/storage_attestation","attest_author":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE/action/author_attestation","sign_citation":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE/action/citation_signature","submit_replication":"https://pith.science/pith/VFSTBZURBIWL6WZTMNXPCNQSHE/action/replication_record"}},"created_at":"2026-07-05T00:45:52.454579+00:00","updated_at":"2026-07-05T00:45:52.454579+00:00"}