{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BZOB7FLXYIKGSWLSZW6AX7LDWW","short_pith_number":"pith:BZOB7FLX","schema_version":"1.0","canonical_sha256":"0e5c1f9577c214695972cdbc0bfd63b5bc7afd87b57da0fe0020ca332b861743","source":{"kind":"arxiv","id":"2605.27428","version":1},"attestation_state":"computed","paper":{"title":"$E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feng Yang, Meixia Tao, Nan Li, Rui Bao, Wenjun Zhang, Yaping Sun, Zhiyong Chen","submitted_at":"2026-05-21T12:32:43Z","abstract_excerpt":"Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time, and it is non-stationary due to user-driven semantic events, background load, and device churn. Consequently, a resource manager that is tuned offline under a fixed regime can become brittle and expensive to maintain. This paper presents $E^3$-Agent, an executable and evolving agent for edge artificial intelligence generated content (AIGC) resource management. $E^3$-Agent separates a fast-path router that makes millisecond-level dispatch deci"},"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":"2605.27428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T12:32:43Z","cross_cats_sorted":[],"title_canon_sha256":"363199980a658455e510acb692ffe2be1446865d8d9ec8c39132e7f9be4e49c8","abstract_canon_sha256":"b8a0fc9fba87c335789550a0f65c7a66a10f5d6a06d425fd5c9c761fb8cc0c0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T00:05:18.293906Z","signature_b64":"1x1PIs4NnKUhSsJ5Og+1JP8h6pM/maLr7zJeCgFoH5MiFcqbBh/cLg6V9/0fGn6FsHHNsy2QSBzJRzDrfY8xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e5c1f9577c214695972cdbc0bfd63b5bc7afd87b57da0fe0020ca332b861743","last_reissued_at":"2026-05-28T00:05:18.293216Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T00:05:18.293216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feng Yang, Meixia Tao, Nan Li, Rui Bao, Wenjun Zhang, Yaping Sun, Zhiyong Chen","submitted_at":"2026-05-21T12:32:43Z","abstract_excerpt":"Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time, and it is non-stationary due to user-driven semantic events, background load, and device churn. Consequently, a resource manager that is tuned offline under a fixed regime can become brittle and expensive to maintain. This paper presents $E^3$-Agent, an executable and evolving agent for edge artificial intelligence generated content (AIGC) resource management. $E^3$-Agent separates a fast-path router that makes millisecond-level dispatch deci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27428","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/2605.27428/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":"2605.27428","created_at":"2026-05-28T00:05:18.293326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27428v1","created_at":"2026-05-28T00:05:18.293326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27428","created_at":"2026-05-28T00:05:18.293326+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZOB7FLXYIKG","created_at":"2026-05-28T00:05:18.293326+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZOB7FLXYIKGSWLS","created_at":"2026-05-28T00:05:18.293326+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZOB7FLX","created_at":"2026-05-28T00:05:18.293326+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/BZOB7FLXYIKGSWLSZW6AX7LDWW","json":"https://pith.science/pith/BZOB7FLXYIKGSWLSZW6AX7LDWW.json","graph_json":"https://pith.science/api/pith-number/BZOB7FLXYIKGSWLSZW6AX7LDWW/graph.json","events_json":"https://pith.science/api/pith-number/BZOB7FLXYIKGSWLSZW6AX7LDWW/events.json","paper":"https://pith.science/paper/BZOB7FLX"},"agent_actions":{"view_html":"https://pith.science/pith/BZOB7FLXYIKGSWLSZW6AX7LDWW","download_json":"https://pith.science/pith/BZOB7FLXYIKGSWLSZW6AX7LDWW.json","view_paper":"https://pith.science/paper/BZOB7FLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27428&json=true","fetch_graph":"https://pith.science/api/pith-number/BZOB7FLXYIKGSWLSZW6AX7LDWW/graph.json","fetch_events":"https://pith.science/api/pith-number/BZOB7FLXYIKGSWLSZW6AX7LDWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZOB7FLXYIKGSWLSZW6AX7LDWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZOB7FLXYIKGSWLSZW6AX7LDWW/action/storage_attestation","attest_author":"https://pith.science/pith/BZOB7FLXYIKGSWLSZW6AX7LDWW/action/author_attestation","sign_citation":"https://pith.science/pith/BZOB7FLXYIKGSWLSZW6AX7LDWW/action/citation_signature","submit_replication":"https://pith.science/pith/BZOB7FLXYIKGSWLSZW6AX7LDWW/action/replication_record"}},"created_at":"2026-05-28T00:05:18.293326+00:00","updated_at":"2026-05-28T00:05:18.293326+00:00"}