{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4665DF5M5S5EBYPYPOGV6J5E5Q","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":"a3e78f17000a8bba04a9e94ade2ffe1c45b8053c4ade02f084d7ff2020394798","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-07T17:56:16Z","title_canon_sha256":"d291adb2f1a62ce48156c92053d24467f536efaf8840df299cfa1d7f9fde84f1"},"schema_version":"1.0","source":{"id":"2411.04919","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04919","created_at":"2026-07-05T09:34:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04919v2","created_at":"2026-07-05T09:34:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04919","created_at":"2026-07-05T09:34:39Z"},{"alias_kind":"pith_short_12","alias_value":"4665DF5M5S5E","created_at":"2026-07-05T09:34:39Z"},{"alias_kind":"pith_short_16","alias_value":"4665DF5M5S5EBYPY","created_at":"2026-07-05T09:34:39Z"},{"alias_kind":"pith_short_8","alias_value":"4665DF5M","created_at":"2026-07-05T09:34:39Z"}],"graph_snapshots":[{"event_id":"sha256:623262409bb4bf6c6383eadf5a9c7569a3ceef4ebc9baa9c63bcf811427a7f94","target":"graph","created_at":"2026-07-05T09:34:39Z","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/2411.04919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual imitation learning methods demonstrate strong performance, yet they lack generalization when faced with visual input perturbations, including variations in lighting and textures, impeding their real-world application. We propose Stem-OB that utilizes pretrained image diffusion models to suppress low-level visual differences while maintaining high-level scene structures. This image inversion process is akin to transforming the observation into a shared representation, from which other observations stem, with extraneous details removed. Stem-OB contrasts with data-augmentation approaches ","authors_text":"Huazhe Xu, Kaizhe Hu, Pu Hua, Yao He, Yuyao Liu, Zihang Rui","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-07T17:56:16Z","title":"Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04919","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:dc4ab190c3a066decd758818d38d1246604fd346a0949fa74964a97df06f4f6a","target":"record","created_at":"2026-07-05T09:34:39Z","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":"a3e78f17000a8bba04a9e94ade2ffe1c45b8053c4ade02f084d7ff2020394798","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-07T17:56:16Z","title_canon_sha256":"d291adb2f1a62ce48156c92053d24467f536efaf8840df299cfa1d7f9fde84f1"},"schema_version":"1.0","source":{"id":"2411.04919","kind":"arxiv","version":2}},"canonical_sha256":"e7bdd197acecba40e1f87b8d5f27a4ec18f370293d49f26dce52bd6f60a5e901","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7bdd197acecba40e1f87b8d5f27a4ec18f370293d49f26dce52bd6f60a5e901","first_computed_at":"2026-07-05T09:34:39.621876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:39.621876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U0mhACjpN+bLmkHlAJTr/LL6gqjS3wUYPplkUe8kdTpzO5fR8eoo7yGXxjPcQO4m3rd41+0KlNNmqLXDdJaRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:39.622369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04919","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc4ab190c3a066decd758818d38d1246604fd346a0949fa74964a97df06f4f6a","sha256:623262409bb4bf6c6383eadf5a9c7569a3ceef4ebc9baa9c63bcf811427a7f94"],"state_sha256":"49100775e2ecc51719bf7648f354e8a440185676ba879b37cf489dda302a75df"}