{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XGGNAC52J2RRSPYB4LQBRDDGDG","short_pith_number":"pith:XGGNAC52","schema_version":"1.0","canonical_sha256":"b98cd00bba4ea3193f01e2e0188c66198c9c6d7112d8efdf3b499f5522576bdd","source":{"kind":"arxiv","id":"2605.18181","version":1},"attestation_state":"computed","paper":{"title":"Scalable Environments Drive Generalizable Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bang Liu, Chenglin Wu, Fanqi Kong, Guibin Zhang, Jianhao Ruan, Jiayi Zhang, Jinyu Xiang, Maojia Song, Yuyu Luo, Zhaoyang Yu","submitted_at":"2026-05-18T10:24:05Z","abstract_excerpt":"Generalizable agents should adapt to diverse tasks and unseen environments beyond their training distribution. This position paper argues that such generalization requires environment scaling: expanding the distribution of executable rule-sets that agents interact with, rather than only increasing trajectories or tasks within fixed benchmarks. Current scaling practices largely focus on collecting more experience or broader task sets under fixed interaction rules, leaving agents brittle when underlying interfaces, dynamics, observations, or feedback signals change. The core challenge is therefo"},"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":"2605.18181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T10:24:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ba666f6919bf8cacaeaaa1248b410b51b85e95750dbd93b14de075b57f69352e","abstract_canon_sha256":"d98ea1a48cfe8f453654ff5359ecf9898c29ef8e6aa69e19028809b20980da1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:49.603684Z","signature_b64":"8fMQwoCSmvM7ZalAvu2/ccM3K3dKL16BMMUU/HvikC9J8AT8kJ+aklipiYCe3R0QXtyj8+yCWpVxTEmwsrBoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b98cd00bba4ea3193f01e2e0188c66198c9c6d7112d8efdf3b499f5522576bdd","last_reissued_at":"2026-05-20T00:05:49.602987Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:49.602987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Environments Drive Generalizable Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bang Liu, Chenglin Wu, Fanqi Kong, Guibin Zhang, Jianhao Ruan, Jiayi Zhang, Jinyu Xiang, Maojia Song, Yuyu Luo, Zhaoyang Yu","submitted_at":"2026-05-18T10:24:05Z","abstract_excerpt":"Generalizable agents should adapt to diverse tasks and unseen environments beyond their training distribution. This position paper argues that such generalization requires environment scaling: expanding the distribution of executable rule-sets that agents interact with, rather than only increasing trajectories or tasks within fixed benchmarks. Current scaling practices largely focus on collecting more experience or broader task sets under fixed interaction rules, leaving agents brittle when underlying interfaces, dynamics, observations, or feedback signals change. The core challenge is therefo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18181","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/2605.18181/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:59.028139Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.342613Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3207311154a7946ccc73bf08cb6458b552d1a3cbf04a09915f9631639108cbd1"},"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":"2605.18181","created_at":"2026-05-20T00:05:49.603087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18181v1","created_at":"2026-05-20T00:05:49.603087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18181","created_at":"2026-05-20T00:05:49.603087+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGGNAC52J2RR","created_at":"2026-05-20T00:05:49.603087+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGGNAC52J2RRSPYB","created_at":"2026-05-20T00:05:49.603087+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGGNAC52","created_at":"2026-05-20T00:05:49.603087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG","json":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG.json","graph_json":"https://pith.science/api/pith-number/XGGNAC52J2RRSPYB4LQBRDDGDG/graph.json","events_json":"https://pith.science/api/pith-number/XGGNAC52J2RRSPYB4LQBRDDGDG/events.json","paper":"https://pith.science/paper/XGGNAC52"},"agent_actions":{"view_html":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG","download_json":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG.json","view_paper":"https://pith.science/paper/XGGNAC52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18181&json=true","fetch_graph":"https://pith.science/api/pith-number/XGGNAC52J2RRSPYB4LQBRDDGDG/graph.json","fetch_events":"https://pith.science/api/pith-number/XGGNAC52J2RRSPYB4LQBRDDGDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG/action/storage_attestation","attest_author":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG/action/author_attestation","sign_citation":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG/action/citation_signature","submit_replication":"https://pith.science/pith/XGGNAC52J2RRSPYB4LQBRDDGDG/action/replication_record"}},"created_at":"2026-05-20T00:05:49.603087+00:00","updated_at":"2026-05-20T00:05:49.603087+00:00"}