{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LCT6ERFB6Q6KC4NXQOYUMG6JHO","short_pith_number":"pith:LCT6ERFB","schema_version":"1.0","canonical_sha256":"58a7e244a1f43ca171b783b1461bc93b867c40aa84eecf83d24ccbad12d81b7e","source":{"kind":"arxiv","id":"1904.12222","version":2},"attestation_state":"computed","paper":{"title":"Collage Inference: Using Coded Redundancy for Low Variance Distributed Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IT","cs.LG","math.IT","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ganesh Ananthanarayanan, Krishna Giri Narra, Murali Annavaram, Salman Avestimehr, Zhifeng Lin","submitted_at":"2019-04-27T22:56:10Z","abstract_excerpt":"MLaaS (ML-as-a-Service) offerings by cloud computing platforms are becoming increasingly popular. Hosting pre-trained machine learning models in the cloud enables elastic scalability as the demand grows. But providing low latency and reducing the latency variance is a key requirement. Variance is harder to control in a cloud deployment due to uncertainties in resource allocations across many virtual instances. We propose the collage inference technique which uses a novel convolutional neural network model, collage-cnn, to provide low-cost redundancy. A collage-cnn model takes a collage image f"},"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":"1904.12222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-27T22:56:10Z","cross_cats_sorted":["cs.DC","cs.IT","cs.LG","math.IT","stat.ML"],"title_canon_sha256":"1acc492a359f2b4f628f78be725e24fe706d38756d0bf44e6f3966582922bf21","abstract_canon_sha256":"4365f3163dabb996c156bffbda5c59ad0a2738be43dae483242dc28f2ef862d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:14.598126Z","signature_b64":"yEGesLybWFY969GKlcy94nxOA3+nZA5Cp+Q31LjyhTFzgb/Y0n/fK32zwA1jiG+YjkGYbRPK3h6YsgqRW3wEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58a7e244a1f43ca171b783b1461bc93b867c40aa84eecf83d24ccbad12d81b7e","last_reissued_at":"2026-07-05T00:03:14.597714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:14.597714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collage Inference: Using Coded Redundancy for Low Variance Distributed Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IT","cs.LG","math.IT","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ganesh Ananthanarayanan, Krishna Giri Narra, Murali Annavaram, Salman Avestimehr, Zhifeng Lin","submitted_at":"2019-04-27T22:56:10Z","abstract_excerpt":"MLaaS (ML-as-a-Service) offerings by cloud computing platforms are becoming increasingly popular. Hosting pre-trained machine learning models in the cloud enables elastic scalability as the demand grows. But providing low latency and reducing the latency variance is a key requirement. Variance is harder to control in a cloud deployment due to uncertainties in resource allocations across many virtual instances. We propose the collage inference technique which uses a novel convolutional neural network model, collage-cnn, to provide low-cost redundancy. A collage-cnn model takes a collage image f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12222","kind":"arxiv","version":2},"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/1904.12222/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":"1904.12222","created_at":"2026-07-05T00:03:14.597768+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.12222v2","created_at":"2026-07-05T00:03:14.597768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12222","created_at":"2026-07-05T00:03:14.597768+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCT6ERFB6Q6K","created_at":"2026-07-05T00:03:14.597768+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCT6ERFB6Q6KC4NX","created_at":"2026-07-05T00:03:14.597768+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCT6ERFB","created_at":"2026-07-05T00:03:14.597768+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/LCT6ERFB6Q6KC4NXQOYUMG6JHO","json":"https://pith.science/pith/LCT6ERFB6Q6KC4NXQOYUMG6JHO.json","graph_json":"https://pith.science/api/pith-number/LCT6ERFB6Q6KC4NXQOYUMG6JHO/graph.json","events_json":"https://pith.science/api/pith-number/LCT6ERFB6Q6KC4NXQOYUMG6JHO/events.json","paper":"https://pith.science/paper/LCT6ERFB"},"agent_actions":{"view_html":"https://pith.science/pith/LCT6ERFB6Q6KC4NXQOYUMG6JHO","download_json":"https://pith.science/pith/LCT6ERFB6Q6KC4NXQOYUMG6JHO.json","view_paper":"https://pith.science/paper/LCT6ERFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.12222&json=true","fetch_graph":"https://pith.science/api/pith-number/LCT6ERFB6Q6KC4NXQOYUMG6JHO/graph.json","fetch_events":"https://pith.science/api/pith-number/LCT6ERFB6Q6KC4NXQOYUMG6JHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCT6ERFB6Q6KC4NXQOYUMG6JHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCT6ERFB6Q6KC4NXQOYUMG6JHO/action/storage_attestation","attest_author":"https://pith.science/pith/LCT6ERFB6Q6KC4NXQOYUMG6JHO/action/author_attestation","sign_citation":"https://pith.science/pith/LCT6ERFB6Q6KC4NXQOYUMG6JHO/action/citation_signature","submit_replication":"https://pith.science/pith/LCT6ERFB6Q6KC4NXQOYUMG6JHO/action/replication_record"}},"created_at":"2026-07-05T00:03:14.597768+00:00","updated_at":"2026-07-05T00:03:14.597768+00:00"}