{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NETIXYAHZLJCIVOYEAMCTGQTNM","short_pith_number":"pith:NETIXYAH","schema_version":"1.0","canonical_sha256":"69268be007cad22455d82018299a136b24077761713a8e9787d00700e2a7a98d","source":{"kind":"arxiv","id":"2306.06997","version":2},"attestation_state":"computed","paper":{"title":"Slot-VAE: Object-Centric Scene Generation with Slot Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Justin Dauwels, Letao Liu, Yanbo Wang","submitted_at":"2023-06-12T09:50:36Z","abstract_excerpt":"Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision. Despite its object-centric binding ability brought by compositional modelling, as a deterministic module, slot attention lacks the ability to generate novel scenes. In this paper, we propose the Slot-VAE, a generative model that integrates slot attention with the hierarchical VAE framework for object-centric structured scene generation. For each image, the model simultaneously infers a global scene representation to capture high-level scene structur"},"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":"2306.06997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T09:50:36Z","cross_cats_sorted":[],"title_canon_sha256":"0658574150081d51e046649996c5d0a8b6d83a52cc49f48cb77c765df40ed26f","abstract_canon_sha256":"d83622b48c0ede7751af0ea56feaac8122172596289e6a9ac07d1b775412a6da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:18.586487Z","signature_b64":"k+kudJlEuuz7ffv5RY9Ng7LR4C533YgrpdB/BHr32ldeb9Wd7bKvvym+GV6vYKXlrja7LKQ/4FZFv1yYvOy9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69268be007cad22455d82018299a136b24077761713a8e9787d00700e2a7a98d","last_reissued_at":"2026-07-05T07:44:18.586117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:18.586117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slot-VAE: Object-Centric Scene Generation with Slot Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Justin Dauwels, Letao Liu, Yanbo Wang","submitted_at":"2023-06-12T09:50:36Z","abstract_excerpt":"Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision. Despite its object-centric binding ability brought by compositional modelling, as a deterministic module, slot attention lacks the ability to generate novel scenes. In this paper, we propose the Slot-VAE, a generative model that integrates slot attention with the hierarchical VAE framework for object-centric structured scene generation. For each image, the model simultaneously infers a global scene representation to capture high-level scene structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06997","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/2306.06997/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":"2306.06997","created_at":"2026-07-05T07:44:18.586174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06997v2","created_at":"2026-07-05T07:44:18.586174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06997","created_at":"2026-07-05T07:44:18.586174+00:00"},{"alias_kind":"pith_short_12","alias_value":"NETIXYAHZLJC","created_at":"2026-07-05T07:44:18.586174+00:00"},{"alias_kind":"pith_short_16","alias_value":"NETIXYAHZLJCIVOY","created_at":"2026-07-05T07:44:18.586174+00:00"},{"alias_kind":"pith_short_8","alias_value":"NETIXYAH","created_at":"2026-07-05T07:44:18.586174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07806","citing_title":"Identifiable Object Representations under Spatial Ambiguities","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM","json":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM.json","graph_json":"https://pith.science/api/pith-number/NETIXYAHZLJCIVOYEAMCTGQTNM/graph.json","events_json":"https://pith.science/api/pith-number/NETIXYAHZLJCIVOYEAMCTGQTNM/events.json","paper":"https://pith.science/paper/NETIXYAH"},"agent_actions":{"view_html":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM","download_json":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM.json","view_paper":"https://pith.science/paper/NETIXYAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06997&json=true","fetch_graph":"https://pith.science/api/pith-number/NETIXYAHZLJCIVOYEAMCTGQTNM/graph.json","fetch_events":"https://pith.science/api/pith-number/NETIXYAHZLJCIVOYEAMCTGQTNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM/action/storage_attestation","attest_author":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM/action/author_attestation","sign_citation":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM/action/citation_signature","submit_replication":"https://pith.science/pith/NETIXYAHZLJCIVOYEAMCTGQTNM/action/replication_record"}},"created_at":"2026-07-05T07:44:18.586174+00:00","updated_at":"2026-07-05T07:44:18.586174+00:00"}