{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RCWUYFXWZEFK3DJTQIVJGTHMTB","short_pith_number":"pith:RCWUYFXW","schema_version":"1.0","canonical_sha256":"88ad4c16f6c90aad8d33822a934cec9840e4ed82f0effbf5e41dcee6cadf9c7a","source":{"kind":"arxiv","id":"2206.01370","version":3},"attestation_state":"computed","paper":{"title":"Towards Improving the Generation Quality of Autoregressive Slot VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anand Rangarajan, Pan He, Patrick Emami, Sanjay Ranka","submitted_at":"2022-06-03T02:41:59Z","abstract_excerpt":"Unconditional scene inference and generation are challenging to learn jointly with a single compositional model. Despite encouraging progress on models that extract object-centric representations (''slots'') from images, unconditional generation of scenes from slots has received less attention. This is primarily because learning the multi-object relations necessary to imagine coherent scenes is difficult. We hypothesize that most existing slot-based models have a limited ability to learn object correlations. We propose two improvements that strengthen object correlation learning. The first is "},"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":"2206.01370","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-03T02:41:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9feb175583a2c1616c1feb0c9b779ff4cb4b404bf245babbce6be088b33cc812","abstract_canon_sha256":"aefd3f72e892eedcb82f5aba46256d26b9753025edad8f711e9755cf7d5ada43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:22.164161Z","signature_b64":"sSgZWmnYn8/wfwzb/CYYM6PPzQvbolGNx9ywTXAmZN6sSvYHdiA/AmJl2t9V8P8noXBy2hqCEy/r+zNTDPGkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88ad4c16f6c90aad8d33822a934cec9840e4ed82f0effbf5e41dcee6cadf9c7a","last_reissued_at":"2026-07-05T07:17:22.163699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:22.163699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Improving the Generation Quality of Autoregressive Slot VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anand Rangarajan, Pan He, Patrick Emami, Sanjay Ranka","submitted_at":"2022-06-03T02:41:59Z","abstract_excerpt":"Unconditional scene inference and generation are challenging to learn jointly with a single compositional model. Despite encouraging progress on models that extract object-centric representations (''slots'') from images, unconditional generation of scenes from slots has received less attention. This is primarily because learning the multi-object relations necessary to imagine coherent scenes is difficult. We hypothesize that most existing slot-based models have a limited ability to learn object correlations. We propose two improvements that strengthen object correlation learning. The first is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01370","kind":"arxiv","version":3},"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/2206.01370/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":"2206.01370","created_at":"2026-07-05T07:17:22.163752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01370v3","created_at":"2026-07-05T07:17:22.163752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01370","created_at":"2026-07-05T07:17:22.163752+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCWUYFXWZEFK","created_at":"2026-07-05T07:17:22.163752+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCWUYFXWZEFK3DJT","created_at":"2026-07-05T07:17:22.163752+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCWUYFXW","created_at":"2026-07-05T07:17:22.163752+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":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB","json":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB.json","graph_json":"https://pith.science/api/pith-number/RCWUYFXWZEFK3DJTQIVJGTHMTB/graph.json","events_json":"https://pith.science/api/pith-number/RCWUYFXWZEFK3DJTQIVJGTHMTB/events.json","paper":"https://pith.science/paper/RCWUYFXW"},"agent_actions":{"view_html":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB","download_json":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB.json","view_paper":"https://pith.science/paper/RCWUYFXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01370&json=true","fetch_graph":"https://pith.science/api/pith-number/RCWUYFXWZEFK3DJTQIVJGTHMTB/graph.json","fetch_events":"https://pith.science/api/pith-number/RCWUYFXWZEFK3DJTQIVJGTHMTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB/action/storage_attestation","attest_author":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB/action/author_attestation","sign_citation":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB/action/citation_signature","submit_replication":"https://pith.science/pith/RCWUYFXWZEFK3DJTQIVJGTHMTB/action/replication_record"}},"created_at":"2026-07-05T07:17:22.163752+00:00","updated_at":"2026-07-05T07:17:22.163752+00:00"}