{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QNQBMBPYXEXMVGMKSN5UFT5IKA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"18e98eb541e322279f94fefc45b421600d5cf77359f7a9336f9bb8fb5300d56f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T10:38:32Z","title_canon_sha256":"c125d279def8571009dd784f598f73436bf8bbc3ebdc94916ee7101917735ba3"},"schema_version":"1.0","source":{"id":"2407.17929","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17929","created_at":"2026-07-05T11:17:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17929v2","created_at":"2026-07-05T11:17:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17929","created_at":"2026-07-05T11:17:34Z"},{"alias_kind":"pith_short_12","alias_value":"QNQBMBPYXEXM","created_at":"2026-07-05T11:17:34Z"},{"alias_kind":"pith_short_16","alias_value":"QNQBMBPYXEXMVGMK","created_at":"2026-07-05T11:17:34Z"},{"alias_kind":"pith_short_8","alias_value":"QNQBMBPY","created_at":"2026-07-05T11:17:34Z"}],"graph_snapshots":[{"event_id":"sha256:f184ef77bd4b9d5937f253d1c81df6f71959410c57fd02b41d4245ef3c339f0c","target":"graph","created_at":"2026-07-05T11:17:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.17929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets, which contain multiple objects of complex textures and shapes in natural everyday scenes. To address this, we introduce Guided Latent Slot Diffusion (GLASS), a novel slot-attention model that learns in the space of generated images and uses semantic and instance guidance modules to learn better slot embeddings for various downstream tasks. Our experiments s","authors_text":"Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T10:38:32Z","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17929","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:62324371528d6d537a1d31e1658516da55aaf3a9b32996c9ba0d8f89cd0eb885","target":"record","created_at":"2026-07-05T11:17:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"18e98eb541e322279f94fefc45b421600d5cf77359f7a9336f9bb8fb5300d56f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T10:38:32Z","title_canon_sha256":"c125d279def8571009dd784f598f73436bf8bbc3ebdc94916ee7101917735ba3"},"schema_version":"1.0","source":{"id":"2407.17929","kind":"arxiv","version":2}},"canonical_sha256":"83601605f8b92eca998a937b42cfa85009a0eff97bf3a45c18b910e6a8e67ea3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83601605f8b92eca998a937b42cfa85009a0eff97bf3a45c18b910e6a8e67ea3","first_computed_at":"2026-07-05T11:17:34.154996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:34.154996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NMF239yRsYUSE5LeXcYFn1W8tpVd6zwTa+ju/jslErGP+nQmkRG2dkSMBO6SEQGPzVlxYlDO9TrE3HsbGJpXBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:34.155489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17929","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62324371528d6d537a1d31e1658516da55aaf3a9b32996c9ba0d8f89cd0eb885","sha256:f184ef77bd4b9d5937f253d1c81df6f71959410c57fd02b41d4245ef3c339f0c"],"state_sha256":"62fb2e62fcd30b4de26d8915f21cc72cef88a7188671c5e234a758cb539fb677"}