{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PDTUVYGY6QZR37RMODMJM6Q74W","short_pith_number":"pith:PDTUVYGY","schema_version":"1.0","canonical_sha256":"78e74ae0d8f4331dfe2c70d8967a1fe5922ba678aec0bad8a1fc38d906e1ba34","source":{"kind":"arxiv","id":"2312.17116","version":1},"attestation_state":"computed","paper":{"title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Huazhe Xu, Yanjie Ze, Yifei Sun, Zhecheng Yuan, Ziyu Wang","submitted_at":"2023-12-28T16:53:23Z","abstract_excerpt":"Learning policies that can generalize to unseen environments is a fundamental challenge in visual reinforcement learning (RL). While most current methods focus on acquiring robust visual representations through auxiliary supervision, pre-training, or data augmentation, the potential of modern vision foundation models remains underleveraged. In this work, we introduce Segment Anything Model for Generalizable visual RL (SAM-G), a novel framework that leverages the promptable segmentation ability of Segment Anything Model (SAM) to enhance the generalization capabilities of visual RL agents. We ut"},"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":"2312.17116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T16:53:23Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"11fa7b096f8407e202fd32e1a03a55e2dc2050e9a4cde48b94bb02283829a724","abstract_canon_sha256":"61695e9da43b0b43374a7a0dece4c197b266bd79cd15de260c7b8452ce928f92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:39.868403Z","signature_b64":"D+OOOZu20jscdjjtTVJur2SCN3LpPr3pz/ihr9kKZdrw5GLUs5HbzOKU5G8GF+oC2JvBmQByozBltSfI4GxhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78e74ae0d8f4331dfe2c70d8967a1fe5922ba678aec0bad8a1fc38d906e1ba34","last_reissued_at":"2026-07-05T07:28:39.868028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:39.868028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Huazhe Xu, Yanjie Ze, Yifei Sun, Zhecheng Yuan, Ziyu Wang","submitted_at":"2023-12-28T16:53:23Z","abstract_excerpt":"Learning policies that can generalize to unseen environments is a fundamental challenge in visual reinforcement learning (RL). While most current methods focus on acquiring robust visual representations through auxiliary supervision, pre-training, or data augmentation, the potential of modern vision foundation models remains underleveraged. In this work, we introduce Segment Anything Model for Generalizable visual RL (SAM-G), a novel framework that leverages the promptable segmentation ability of Segment Anything Model (SAM) to enhance the generalization capabilities of visual RL agents. We ut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17116","kind":"arxiv","version":1},"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/2312.17116/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":"2312.17116","created_at":"2026-07-05T07:28:39.868081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17116v1","created_at":"2026-07-05T07:28:39.868081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17116","created_at":"2026-07-05T07:28:39.868081+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDTUVYGY6QZR","created_at":"2026-07-05T07:28:39.868081+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDTUVYGY6QZR37RM","created_at":"2026-07-05T07:28:39.868081+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDTUVYGY","created_at":"2026-07-05T07:28:39.868081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00796","citing_title":"Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24661","citing_title":"Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24661","citing_title":"Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W","json":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W.json","graph_json":"https://pith.science/api/pith-number/PDTUVYGY6QZR37RMODMJM6Q74W/graph.json","events_json":"https://pith.science/api/pith-number/PDTUVYGY6QZR37RMODMJM6Q74W/events.json","paper":"https://pith.science/paper/PDTUVYGY"},"agent_actions":{"view_html":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W","download_json":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W.json","view_paper":"https://pith.science/paper/PDTUVYGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17116&json=true","fetch_graph":"https://pith.science/api/pith-number/PDTUVYGY6QZR37RMODMJM6Q74W/graph.json","fetch_events":"https://pith.science/api/pith-number/PDTUVYGY6QZR37RMODMJM6Q74W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W/action/storage_attestation","attest_author":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W/action/author_attestation","sign_citation":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W/action/citation_signature","submit_replication":"https://pith.science/pith/PDTUVYGY6QZR37RMODMJM6Q74W/action/replication_record"}},"created_at":"2026-07-05T07:28:39.868081+00:00","updated_at":"2026-07-05T07:28:39.868081+00:00"}