{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QNQBMBPYXEXMVGMKSN5UFT5IKA","short_pith_number":"pith:QNQBMBPY","schema_version":"1.0","canonical_sha256":"83601605f8b92eca998a937b42cfa85009a0eff97bf3a45c18b910e6a8e67ea3","source":{"kind":"arxiv","id":"2407.17929","version":2},"attestation_state":"computed","paper":{"title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth","submitted_at":"2024-07-25T10:38:32Z","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"},"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":"2407.17929","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T10:38:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c125d279def8571009dd784f598f73436bf8bbc3ebdc94916ee7101917735ba3","abstract_canon_sha256":"18e98eb541e322279f94fefc45b421600d5cf77359f7a9336f9bb8fb5300d56f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:34.155489Z","signature_b64":"NMF239yRsYUSE5LeXcYFn1W8tpVd6zwTa+ju/jslErGP+nQmkRG2dkSMBO6SEQGPzVlxYlDO9TrE3HsbGJpXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83601605f8b92eca998a937b42cfa85009a0eff97bf3a45c18b910e6a8e67ea3","last_reissued_at":"2026-07-05T11:17:34.154996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:34.154996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth","submitted_at":"2024-07-25T10:38:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17929","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/2407.17929/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":"2407.17929","created_at":"2026-07-05T11:17:34.155057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17929v2","created_at":"2026-07-05T11:17:34.155057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17929","created_at":"2026-07-05T11:17:34.155057+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNQBMBPYXEXM","created_at":"2026-07-05T11:17:34.155057+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNQBMBPYXEXMVGMK","created_at":"2026-07-05T11:17:34.155057+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNQBMBPY","created_at":"2026-07-05T11:17:34.155057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15878","citing_title":"Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA","json":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA.json","graph_json":"https://pith.science/api/pith-number/QNQBMBPYXEXMVGMKSN5UFT5IKA/graph.json","events_json":"https://pith.science/api/pith-number/QNQBMBPYXEXMVGMKSN5UFT5IKA/events.json","paper":"https://pith.science/paper/QNQBMBPY"},"agent_actions":{"view_html":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA","download_json":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA.json","view_paper":"https://pith.science/paper/QNQBMBPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17929&json=true","fetch_graph":"https://pith.science/api/pith-number/QNQBMBPYXEXMVGMKSN5UFT5IKA/graph.json","fetch_events":"https://pith.science/api/pith-number/QNQBMBPYXEXMVGMKSN5UFT5IKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA/action/storage_attestation","attest_author":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA/action/author_attestation","sign_citation":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA/action/citation_signature","submit_replication":"https://pith.science/pith/QNQBMBPYXEXMVGMKSN5UFT5IKA/action/replication_record"}},"created_at":"2026-07-05T11:17:34.155057+00:00","updated_at":"2026-07-05T11:17:34.155057+00:00"}