{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4PCQGNCVOPD4RO3SHQYXEXEKVE","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":"0401b5def5cace85a39304062bae0034cd804caefc1129f235dc9b5bc715e930","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T15:43:54Z","title_canon_sha256":"69475527086a64d766b2fb00f36191c1a076cb6115c1ef78248e8ea768d2efaf"},"schema_version":"1.0","source":{"id":"2407.03216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03216","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03216v1","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03216","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"4PCQGNCVOPD4","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"pith_short_16","alias_value":"4PCQGNCVOPD4RO3S","created_at":"2026-07-05T08:39:47Z"},{"alias_kind":"pith_short_8","alias_value":"4PCQGNCV","created_at":"2026-07-05T08:39:47Z"}],"graph_snapshots":[{"event_id":"sha256:1c537c79fb43b437916f59427425526e1ba0b11645ab8318f3b313d99e7a66d2","target":"graph","created_at":"2026-07-05T08:39:47Z","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/2407.03216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: \"can learning disentangled representation further improve the accuracy of visual dynamics prediction in object-centric models?\" While there has been some attempt to learn such disentangled representations for the case of static images \\citep{nsb}, to the best of our knowledge, ours is the first work which tries to do this in a general setting for video, without mak","authors_text":"Arnab Kumar Mondal, Atul, Parag Singla, Rushil Gupta, Samanyu Mahajan, Sanket Gandhi, Vishal Sharma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T15:43:54Z","title":"Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03216","kind":"arxiv","version":1},"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:d7a1f3f521cf77138cbe5289266ee143619880b6edbdfaeb321b7663482b0d51","target":"record","created_at":"2026-07-05T08:39:47Z","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":"0401b5def5cace85a39304062bae0034cd804caefc1129f235dc9b5bc715e930","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T15:43:54Z","title_canon_sha256":"69475527086a64d766b2fb00f36191c1a076cb6115c1ef78248e8ea768d2efaf"},"schema_version":"1.0","source":{"id":"2407.03216","kind":"arxiv","version":1}},"canonical_sha256":"e3c503345573c7c8bb723c31725c8aa90c12a8db477a54d48e976fa9c79898b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3c503345573c7c8bb723c31725c8aa90c12a8db477a54d48e976fa9c79898b6","first_computed_at":"2026-07-05T08:39:47.890514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:47.890514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"03Q5cIn5Q8AefyP31B6aImKpgTgc1yZQdybQU9SRNSgEHfV3x2jai1DHzASruRxUoKUj6RmPTJzmCceaRhpUAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:47.890956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7a1f3f521cf77138cbe5289266ee143619880b6edbdfaeb321b7663482b0d51","sha256:1c537c79fb43b437916f59427425526e1ba0b11645ab8318f3b313d99e7a66d2"],"state_sha256":"9e917d9e58f4c84141ccedf82acce3ff924d7525f8f48934748bcf327806e75c"}