{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XMJKWP3QIARRQW7NNZ47Q2U2KW","short_pith_number":"pith:XMJKWP3Q","schema_version":"1.0","canonical_sha256":"bb12ab3f704023185bed6e79f86a9a55acf9d6037b1438818dbfe0b3dfbc3f97","source":{"kind":"arxiv","id":"2507.14802","version":1},"attestation_state":"computed","paper":{"title":"ACME: Adaptive Customization of Large Models via Distributed Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Chao Qiu, Fei Gao, Xiaofei Wang, Yunfeng Zhao, Ziming Dai","submitted_at":"2025-07-20T03:30:24Z","abstract_excerpt":"Pre-trained Transformer-based large models have revolutionized personal virtual assistants, but their deployment in cloud environments faces challenges related to data privacy and response latency. Deploying large models closer to the data and users has become a key research area to address these issues. However, applying these models directly often entails significant difficulties, such as model mismatching, resource constraints, and energy inefficiency. Automated design of customized models is necessary, but it faces three key challenges, namely, the high cost of centralized model customizat"},"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":"2507.14802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-07-20T03:30:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed80dcc0ec1d11db5e8cf9f3f1452d966dde6951e0ceb71851f5e8bf07cea051","abstract_canon_sha256":"2972e58b81a1248f74f208865a285cde5b41fc3d9f583bbc1d0381cc5105bf9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:13.821081Z","signature_b64":"fu/F9AlvjJKTKAm2rM+Hv3blVAmIMD3qILN7C3h7FK4C42u/4D0Wot8KJDRlqJBAQwnq/P3UDVSeTBLW1pW0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb12ab3f704023185bed6e79f86a9a55acf9d6037b1438818dbfe0b3dfbc3f97","last_reissued_at":"2026-07-05T11:40:13.820600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:13.820600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACME: Adaptive Customization of Large Models via Distributed Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Chao Qiu, Fei Gao, Xiaofei Wang, Yunfeng Zhao, Ziming Dai","submitted_at":"2025-07-20T03:30:24Z","abstract_excerpt":"Pre-trained Transformer-based large models have revolutionized personal virtual assistants, but their deployment in cloud environments faces challenges related to data privacy and response latency. Deploying large models closer to the data and users has become a key research area to address these issues. However, applying these models directly often entails significant difficulties, such as model mismatching, resource constraints, and energy inefficiency. Automated design of customized models is necessary, but it faces three key challenges, namely, the high cost of centralized model customizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14802","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/2507.14802/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":"2507.14802","created_at":"2026-07-05T11:40:13.820657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14802v1","created_at":"2026-07-05T11:40:13.820657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14802","created_at":"2026-07-05T11:40:13.820657+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMJKWP3QIARR","created_at":"2026-07-05T11:40:13.820657+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMJKWP3QIARRQW7N","created_at":"2026-07-05T11:40:13.820657+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMJKWP3Q","created_at":"2026-07-05T11:40:13.820657+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/XMJKWP3QIARRQW7NNZ47Q2U2KW","json":"https://pith.science/pith/XMJKWP3QIARRQW7NNZ47Q2U2KW.json","graph_json":"https://pith.science/api/pith-number/XMJKWP3QIARRQW7NNZ47Q2U2KW/graph.json","events_json":"https://pith.science/api/pith-number/XMJKWP3QIARRQW7NNZ47Q2U2KW/events.json","paper":"https://pith.science/paper/XMJKWP3Q"},"agent_actions":{"view_html":"https://pith.science/pith/XMJKWP3QIARRQW7NNZ47Q2U2KW","download_json":"https://pith.science/pith/XMJKWP3QIARRQW7NNZ47Q2U2KW.json","view_paper":"https://pith.science/paper/XMJKWP3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14802&json=true","fetch_graph":"https://pith.science/api/pith-number/XMJKWP3QIARRQW7NNZ47Q2U2KW/graph.json","fetch_events":"https://pith.science/api/pith-number/XMJKWP3QIARRQW7NNZ47Q2U2KW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMJKWP3QIARRQW7NNZ47Q2U2KW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMJKWP3QIARRQW7NNZ47Q2U2KW/action/storage_attestation","attest_author":"https://pith.science/pith/XMJKWP3QIARRQW7NNZ47Q2U2KW/action/author_attestation","sign_citation":"https://pith.science/pith/XMJKWP3QIARRQW7NNZ47Q2U2KW/action/citation_signature","submit_replication":"https://pith.science/pith/XMJKWP3QIARRQW7NNZ47Q2U2KW/action/replication_record"}},"created_at":"2026-07-05T11:40:13.820657+00:00","updated_at":"2026-07-05T11:40:13.820657+00:00"}