{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CSIE6OUI32TMGIEUEOVAOHYBMA","short_pith_number":"pith:CSIE6OUI","schema_version":"1.0","canonical_sha256":"14904f3a88dea6c3209423aa071f016017938050324acde0908b28367989ff92","source":{"kind":"arxiv","id":"2608.08036","version":1},"attestation_state":"computed","paper":{"title":"Compiling and Benchmarking Task-State Horizons for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Meiqi Wang, Shichao Li","submitted_at":"2026-08-08T09:45:01Z","abstract_excerpt":"Frontier agentic models are increasingly deployed as high-level planners for long-horizon embodied tasks. Existing robotic benchmarks have advanced long-horizon evaluation, but primarily characterize difficulty through action-sequence length and subtask complexity, overlooking a distinct challenge: agents must track evolving task-relevant world states induced by both their exploration and environmental dynamics. We define the span of task-relevant state transitions that an agent must track as task-state horizon (TSH). To evaluate how agent performance varies with TSH, we introduce RoboGraph, a"},"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":"2608.08036","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-08T09:45:01Z","cross_cats_sorted":[],"title_canon_sha256":"3daaea417cb1bd4752b90692182ad009de0e07fa20e3d790f189a2d86a5c5e01","abstract_canon_sha256":"51dfd4d2378dd60ad081e0bafd7506b03bc7820c7e7b53af23195579e5dcde2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:21:28.768457Z","signature_b64":"AM2uYid99jbVzxtQaQ7TZ02/3rNfjIBp2R4A10SIHc/IrfrRo4GVCHad0+m76EjNT0kEovmWY9YXK7E0XlM1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14904f3a88dea6c3209423aa071f016017938050324acde0908b28367989ff92","last_reissued_at":"2026-08-11T01:21:28.765886Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:21:28.765886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compiling and Benchmarking Task-State Horizons for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Meiqi Wang, Shichao Li","submitted_at":"2026-08-08T09:45:01Z","abstract_excerpt":"Frontier agentic models are increasingly deployed as high-level planners for long-horizon embodied tasks. Existing robotic benchmarks have advanced long-horizon evaluation, but primarily characterize difficulty through action-sequence length and subtask complexity, overlooking a distinct challenge: agents must track evolving task-relevant world states induced by both their exploration and environmental dynamics. We define the span of task-relevant state transitions that an agent must track as task-state horizon (TSH). To evaluate how agent performance varies with TSH, we introduce RoboGraph, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08036","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/2608.08036/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":"2608.08036","created_at":"2026-08-11T01:21:28.766751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08036v1","created_at":"2026-08-11T01:21:28.766751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08036","created_at":"2026-08-11T01:21:28.766751+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSIE6OUI32TM","created_at":"2026-08-11T01:21:28.766751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSIE6OUI32TMGIEU","created_at":"2026-08-11T01:21:28.766751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSIE6OUI","created_at":"2026-08-11T01:21:28.766751+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/CSIE6OUI32TMGIEUEOVAOHYBMA","json":"https://pith.science/pith/CSIE6OUI32TMGIEUEOVAOHYBMA.json","graph_json":"https://pith.science/api/pith-number/CSIE6OUI32TMGIEUEOVAOHYBMA/graph.json","events_json":"https://pith.science/api/pith-number/CSIE6OUI32TMGIEUEOVAOHYBMA/events.json","paper":"https://pith.science/paper/CSIE6OUI"},"agent_actions":{"view_html":"https://pith.science/pith/CSIE6OUI32TMGIEUEOVAOHYBMA","download_json":"https://pith.science/pith/CSIE6OUI32TMGIEUEOVAOHYBMA.json","view_paper":"https://pith.science/paper/CSIE6OUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08036&json=true","fetch_graph":"https://pith.science/api/pith-number/CSIE6OUI32TMGIEUEOVAOHYBMA/graph.json","fetch_events":"https://pith.science/api/pith-number/CSIE6OUI32TMGIEUEOVAOHYBMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSIE6OUI32TMGIEUEOVAOHYBMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSIE6OUI32TMGIEUEOVAOHYBMA/action/storage_attestation","attest_author":"https://pith.science/pith/CSIE6OUI32TMGIEUEOVAOHYBMA/action/author_attestation","sign_citation":"https://pith.science/pith/CSIE6OUI32TMGIEUEOVAOHYBMA/action/citation_signature","submit_replication":"https://pith.science/pith/CSIE6OUI32TMGIEUEOVAOHYBMA/action/replication_record"}},"created_at":"2026-08-11T01:21:28.766751+00:00","updated_at":"2026-08-11T01:21:28.766751+00:00"}