{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AF6RINUTVXJ2CRZHQEDFMK6MW7","short_pith_number":"pith:AF6RINUT","schema_version":"1.0","canonical_sha256":"017d143693add3a147278106562bccb7ef3bf91cdb45567ca83d89c9cc7fdbb5","source":{"kind":"arxiv","id":"2302.13155","version":1},"attestation_state":"computed","paper":{"title":"Efficient Multitask Learning on Resource-Constrained Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Le Zhang, Shahriar Nirjon (University of North Carolina at Chapel Hill), Yubo Luo, Zhenyu Wang","submitted_at":"2023-02-25T20:54:00Z","abstract_excerpt":"We present Antler, which exploits the affinity between all pairs of tasks in a multitask inference system to construct a compact graph representation of the task set and finds an optimal order of execution of the tasks such that the end-to-end time and energy cost of inference is reduced while the accuracy remains similar to the state-of-the-art. The design of Antler is based on two observations: first, tasks running on the same platform shows affinity, which is leveraged to find a compact graph representation of the tasks that helps avoid unnecessary computations of overlapping subtasks in th"},"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":"2302.13155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-02-25T20:54:00Z","cross_cats_sorted":[],"title_canon_sha256":"e0ab27cf346a42f3bedaf1b1a05607bd8047b37da096294badb5a4ead51be1c3","abstract_canon_sha256":"54c6a7afd5dfe3434a92a4812bf1e021f9514cd321432ef943c76b54e246660d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:43.694402Z","signature_b64":"F3X/GbIaYJJ7wUnmHBoOIcEw4GtOOe2Eynnlok6CfEBa8N6LujWU90x0ahGKmG6VQ/hqoUHN9b8O5vj2pu2pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"017d143693add3a147278106562bccb7ef3bf91cdb45567ca83d89c9cc7fdbb5","last_reissued_at":"2026-07-05T05:45:43.694037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:43.694037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Multitask Learning on Resource-Constrained Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Le Zhang, Shahriar Nirjon (University of North Carolina at Chapel Hill), Yubo Luo, Zhenyu Wang","submitted_at":"2023-02-25T20:54:00Z","abstract_excerpt":"We present Antler, which exploits the affinity between all pairs of tasks in a multitask inference system to construct a compact graph representation of the task set and finds an optimal order of execution of the tasks such that the end-to-end time and energy cost of inference is reduced while the accuracy remains similar to the state-of-the-art. The design of Antler is based on two observations: first, tasks running on the same platform shows affinity, which is leveraged to find a compact graph representation of the tasks that helps avoid unnecessary computations of overlapping subtasks in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13155","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/2302.13155/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":"2302.13155","created_at":"2026-07-05T05:45:43.694095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13155v1","created_at":"2026-07-05T05:45:43.694095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13155","created_at":"2026-07-05T05:45:43.694095+00:00"},{"alias_kind":"pith_short_12","alias_value":"AF6RINUTVXJ2","created_at":"2026-07-05T05:45:43.694095+00:00"},{"alias_kind":"pith_short_16","alias_value":"AF6RINUTVXJ2CRZH","created_at":"2026-07-05T05:45:43.694095+00:00"},{"alias_kind":"pith_short_8","alias_value":"AF6RINUT","created_at":"2026-07-05T05:45:43.694095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14185","citing_title":"Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7","json":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7.json","graph_json":"https://pith.science/api/pith-number/AF6RINUTVXJ2CRZHQEDFMK6MW7/graph.json","events_json":"https://pith.science/api/pith-number/AF6RINUTVXJ2CRZHQEDFMK6MW7/events.json","paper":"https://pith.science/paper/AF6RINUT"},"agent_actions":{"view_html":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7","download_json":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7.json","view_paper":"https://pith.science/paper/AF6RINUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13155&json=true","fetch_graph":"https://pith.science/api/pith-number/AF6RINUTVXJ2CRZHQEDFMK6MW7/graph.json","fetch_events":"https://pith.science/api/pith-number/AF6RINUTVXJ2CRZHQEDFMK6MW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7/action/storage_attestation","attest_author":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7/action/author_attestation","sign_citation":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7/action/citation_signature","submit_replication":"https://pith.science/pith/AF6RINUTVXJ2CRZHQEDFMK6MW7/action/replication_record"}},"created_at":"2026-07-05T05:45:43.694095+00:00","updated_at":"2026-07-05T05:45:43.694095+00:00"}