{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4J5JAHZJVT2CDQPTPXN7SL6RS2","short_pith_number":"pith:4J5JAHZJ","schema_version":"1.0","canonical_sha256":"e27a901f29acf421c1f37ddbf92fd1969575981a2c1f97791c241dddff2c2203","source":{"kind":"arxiv","id":"1911.12247","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Learning of Structured World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Elise van der Pol, Max Welling, Thomas Kipf","submitted_at":"2019-11-27T16:10:04Z","abstract_excerpt":"A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs utilize a contrastive approach for representation learning in environments with compositional structure. We structure each state embedding as a set of object representations and their relations, modeled by a graph neural network. This allows objects to be discovered from raw pix"},"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":"1911.12247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-27T16:10:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"df2f3f1ef7e950d660535a14eaa9bf4f03e69b15989ab6b51c53c0d55f02ad5d","abstract_canon_sha256":"690f5e6e9470c632ba853be412e61895b91d9e1f6ce1d28268f870f16c9d9598"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:41.454796Z","signature_b64":"CIObUeLzFVwdKRjcwVwA02jmkw/Yqn9sF532dAC9O7OCZE2xbsivwxBi2bQmYO1gI5XgWLDm5RgD+wx3tNlcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e27a901f29acf421c1f37ddbf92fd1969575981a2c1f97791c241dddff2c2203","last_reissued_at":"2026-07-05T00:29:41.454256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:41.454256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Learning of Structured World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Elise van der Pol, Max Welling, Thomas Kipf","submitted_at":"2019-11-27T16:10:04Z","abstract_excerpt":"A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs utilize a contrastive approach for representation learning in environments with compositional structure. We structure each state embedding as a set of object representations and their relations, modeled by a graph neural network. This allows objects to be discovered from raw pix"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12247","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/1911.12247/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":"1911.12247","created_at":"2026-07-05T00:29:41.454324+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.12247v2","created_at":"2026-07-05T00:29:41.454324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12247","created_at":"2026-07-05T00:29:41.454324+00:00"},{"alias_kind":"pith_short_12","alias_value":"4J5JAHZJVT2C","created_at":"2026-07-05T00:29:41.454324+00:00"},{"alias_kind":"pith_short_16","alias_value":"4J5JAHZJVT2CDQPT","created_at":"2026-07-05T00:29:41.454324+00:00"},{"alias_kind":"pith_short_8","alias_value":"4J5JAHZJ","created_at":"2026-07-05T00:29:41.454324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06401","citing_title":"A Definition and Roadmap for World Models","ref_index":134,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06832","citing_title":"STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from Images","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00620","citing_title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","ref_index":208,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18878","citing_title":"Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07712","citing_title":"CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16678","citing_title":"UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2","json":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2.json","graph_json":"https://pith.science/api/pith-number/4J5JAHZJVT2CDQPTPXN7SL6RS2/graph.json","events_json":"https://pith.science/api/pith-number/4J5JAHZJVT2CDQPTPXN7SL6RS2/events.json","paper":"https://pith.science/paper/4J5JAHZJ"},"agent_actions":{"view_html":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2","download_json":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2.json","view_paper":"https://pith.science/paper/4J5JAHZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.12247&json=true","fetch_graph":"https://pith.science/api/pith-number/4J5JAHZJVT2CDQPTPXN7SL6RS2/graph.json","fetch_events":"https://pith.science/api/pith-number/4J5JAHZJVT2CDQPTPXN7SL6RS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2/action/storage_attestation","attest_author":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2/action/author_attestation","sign_citation":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2/action/citation_signature","submit_replication":"https://pith.science/pith/4J5JAHZJVT2CDQPTPXN7SL6RS2/action/replication_record"}},"created_at":"2026-07-05T00:29:41.454324+00:00","updated_at":"2026-07-05T00:29:41.454324+00:00"}