{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ALV2ILAQRUTGAEDBU2ARDYPAZF","short_pith_number":"pith:ALV2ILAQ","schema_version":"1.0","canonical_sha256":"02eba42c108d26601061a68111e1e0c95a26e63c4f88653508c4b320a792084f","source":{"kind":"arxiv","id":"2605.20723","version":1},"attestation_state":"computed","paper":{"title":"Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Disumi Pathirana, Kutila Gunasekera, Lakshani Manamperi, Nipun Premarathna, Thiwanka Pathirana","submitted_at":"2026-05-20T05:21:54Z","abstract_excerpt":"Deploying large deep neural networks on memory-constrained mobile devices is a central challenge in edge ML. While compression, pruning, and quantization reduce per-parameter cost, transformer-based models remain too large for the 3.3-7.4 GB RAM envelope of commodity Android handsets. We present the DNN pipeline scheduling subsystem of CROWDio, which achieves practical ONNX inference across resource-constrained Android workers without model modification, by distributing memory pressure across devices via five mechanisms: JIT deferred partition loading, a single-partition-resident constraint, 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":"2605.20723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:21:54Z","cross_cats_sorted":[],"title_canon_sha256":"de1af3df1eab8f9a8f656aadcd2b8cdc1de531b41ac1c7f0ad3a8ea1affa1302","abstract_canon_sha256":"9c8e85f656f5a1f45a6d0535d0b47686fc4c99550f988d16d78c726fcdcce915"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:50.842828Z","signature_b64":"crbplAxaRmormeYCGTZ4E31rI0UqqbWEjr8Zlit+fgQ2j4TDEAZe5nRcEkBC9V41yvEii1qtoFReCaQMIDU5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02eba42c108d26601061a68111e1e0c95a26e63c4f88653508c4b320a792084f","last_reissued_at":"2026-05-21T01:04:50.842080Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:50.842080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Disumi Pathirana, Kutila Gunasekera, Lakshani Manamperi, Nipun Premarathna, Thiwanka Pathirana","submitted_at":"2026-05-20T05:21:54Z","abstract_excerpt":"Deploying large deep neural networks on memory-constrained mobile devices is a central challenge in edge ML. While compression, pruning, and quantization reduce per-parameter cost, transformer-based models remain too large for the 3.3-7.4 GB RAM envelope of commodity Android handsets. We present the DNN pipeline scheduling subsystem of CROWDio, which achieves practical ONNX inference across resource-constrained Android workers without model modification, by distributing memory pressure across devices via five mechanisms: JIT deferred partition loading, a single-partition-resident constraint, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20723","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/2605.20723/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":"2605.20723","created_at":"2026-05-21T01:04:50.842216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20723v1","created_at":"2026-05-21T01:04:50.842216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20723","created_at":"2026-05-21T01:04:50.842216+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALV2ILAQRUTG","created_at":"2026-05-21T01:04:50.842216+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALV2ILAQRUTGAEDB","created_at":"2026-05-21T01:04:50.842216+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALV2ILAQ","created_at":"2026-05-21T01:04:50.842216+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/ALV2ILAQRUTGAEDBU2ARDYPAZF","json":"https://pith.science/pith/ALV2ILAQRUTGAEDBU2ARDYPAZF.json","graph_json":"https://pith.science/api/pith-number/ALV2ILAQRUTGAEDBU2ARDYPAZF/graph.json","events_json":"https://pith.science/api/pith-number/ALV2ILAQRUTGAEDBU2ARDYPAZF/events.json","paper":"https://pith.science/paper/ALV2ILAQ"},"agent_actions":{"view_html":"https://pith.science/pith/ALV2ILAQRUTGAEDBU2ARDYPAZF","download_json":"https://pith.science/pith/ALV2ILAQRUTGAEDBU2ARDYPAZF.json","view_paper":"https://pith.science/paper/ALV2ILAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20723&json=true","fetch_graph":"https://pith.science/api/pith-number/ALV2ILAQRUTGAEDBU2ARDYPAZF/graph.json","fetch_events":"https://pith.science/api/pith-number/ALV2ILAQRUTGAEDBU2ARDYPAZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALV2ILAQRUTGAEDBU2ARDYPAZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALV2ILAQRUTGAEDBU2ARDYPAZF/action/storage_attestation","attest_author":"https://pith.science/pith/ALV2ILAQRUTGAEDBU2ARDYPAZF/action/author_attestation","sign_citation":"https://pith.science/pith/ALV2ILAQRUTGAEDBU2ARDYPAZF/action/citation_signature","submit_replication":"https://pith.science/pith/ALV2ILAQRUTGAEDBU2ARDYPAZF/action/replication_record"}},"created_at":"2026-05-21T01:04:50.842216+00:00","updated_at":"2026-05-21T01:04:50.842216+00:00"}