{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TFGYBWYTFTCS3PTRW2KEVXFM2J","short_pith_number":"pith:TFGYBWYT","canonical_record":{"source":{"id":"1802.00699","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-01T04:26:21Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"4c2f872da26fe489cf40d23c10ab6507bcaab9614aee2264bf4fbdc3cc2d07e8","abstract_canon_sha256":"50c3a46cb1addd5cbd1d4c4d375130240fb63ab3f20dbff3a42e645727685d03"},"schema_version":"1.0"},"canonical_sha256":"994d80db132cc52dbe71b6944adcacd2493793cbcd0e69e8351c034587b14056","source":{"kind":"arxiv","id":"1802.00699","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00699","created_at":"2026-05-18T00:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00699v2","created_at":"2026-05-18T00:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00699","created_at":"2026-05-18T00:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"TFGYBWYTFTCS","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TFGYBWYTFTCS3PTR","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TFGYBWYT","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TFGYBWYTFTCS3PTRW2KEVXFM2J","target":"record","payload":{"canonical_record":{"source":{"id":"1802.00699","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-01T04:26:21Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"4c2f872da26fe489cf40d23c10ab6507bcaab9614aee2264bf4fbdc3cc2d07e8","abstract_canon_sha256":"50c3a46cb1addd5cbd1d4c4d375130240fb63ab3f20dbff3a42e645727685d03"},"schema_version":"1.0"},"canonical_sha256":"994d80db132cc52dbe71b6944adcacd2493793cbcd0e69e8351c034587b14056","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:50.194620Z","signature_b64":"iIF9UOBGoFo8/QPUhRzRebnMwanlfgohQ5eYGWPbOK/slwcRPA4nX05tT2mBqE7OkId4KpFn4GXCp2tg2KaEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"994d80db132cc52dbe71b6944adcacd2493793cbcd0e69e8351c034587b14056","last_reissued_at":"2026-05-18T00:16:50.193641Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:50.193641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.00699","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xh+1qnVBTtPeMNTAZzIP8jOG4woUY6RMuUke4wlC54U/RtIsvYRdg7nhH/hrWdD9A3RJhSs0L6YfDNv+5gglCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T14:48:28.066735Z"},"content_sha256":"c087c8016eb312e167c8b74bafabdc07531e5a37e3588053612202d99a10d154","schema_version":"1.0","event_id":"sha256:c087c8016eb312e167c8b74bafabdc07531e5a37e3588053612202d99a10d154"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TFGYBWYTFTCS3PTRW2KEVXFM2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Dwarfs: A Lens Towards Fully Understanding Big Data and AI Workloads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Biwei Xie, Chen Zheng, Chunjie Luo, Daoyi Zheng, Fei Tang, Jianfeng Zhan, Lei Wang, Qiang Yang, Wanling Gao","submitted_at":"2018-02-01T04:26:21Z","abstract_excerpt":"The complexity and diversity of big data and AI workloads make understanding them difficult and challenging. This paper proposes a new approach to characterizing big data and AI workloads. We consider each big data and AI workload as a pipeline of one or more classes of unit of computations performed on different initial or intermediate data inputs. Each class of unit of computation captures the common requirements while being reasonably divorced from individual implementations, and hence we call it a data dwarf. For the first time, among a wide variety of big data and AI workloads, we identif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00699","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X5pdun9Xmc+KmeIUpTaOyFaxeui9Q/4a+KwWs8Ru91HmwKqw6BD+MFweSlWRGjUb6YwGx5YPm3imiiZJiV4iDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T14:48:28.067391Z"},"content_sha256":"522bfed9d38d2ca7b89b024689d528ceeb2331f5b22a5f43b598d5495db6f254","schema_version":"1.0","event_id":"sha256:522bfed9d38d2ca7b89b024689d528ceeb2331f5b22a5f43b598d5495db6f254"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TFGYBWYTFTCS3PTRW2KEVXFM2J/bundle.json","state_url":"https://pith.science/pith/TFGYBWYTFTCS3PTRW2KEVXFM2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TFGYBWYTFTCS3PTRW2KEVXFM2J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T14:48:28Z","links":{"resolver":"https://pith.science/pith/TFGYBWYTFTCS3PTRW2KEVXFM2J","bundle":"https://pith.science/pith/TFGYBWYTFTCS3PTRW2KEVXFM2J/bundle.json","state":"https://pith.science/pith/TFGYBWYTFTCS3PTRW2KEVXFM2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TFGYBWYTFTCS3PTRW2KEVXFM2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TFGYBWYTFTCS3PTRW2KEVXFM2J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"50c3a46cb1addd5cbd1d4c4d375130240fb63ab3f20dbff3a42e645727685d03","cross_cats_sorted":["cs.PF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-01T04:26:21Z","title_canon_sha256":"4c2f872da26fe489cf40d23c10ab6507bcaab9614aee2264bf4fbdc3cc2d07e8"},"schema_version":"1.0","source":{"id":"1802.00699","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00699","created_at":"2026-05-18T00:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00699v2","created_at":"2026-05-18T00:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00699","created_at":"2026-05-18T00:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"TFGYBWYTFTCS","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TFGYBWYTFTCS3PTR","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TFGYBWYT","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:522bfed9d38d2ca7b89b024689d528ceeb2331f5b22a5f43b598d5495db6f254","target":"graph","created_at":"2026-05-18T00:16:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The complexity and diversity of big data and AI workloads make understanding them difficult and challenging. This paper proposes a new approach to characterizing big data and AI workloads. We consider each big data and AI workload as a pipeline of one or more classes of unit of computations performed on different initial or intermediate data inputs. Each class of unit of computation captures the common requirements while being reasonably divorced from individual implementations, and hence we call it a data dwarf. For the first time, among a wide variety of big data and AI workloads, we identif","authors_text":"Biwei Xie, Chen Zheng, Chunjie Luo, Daoyi Zheng, Fei Tang, Jianfeng Zhan, Lei Wang, Qiang Yang, Wanling Gao","cross_cats":["cs.PF"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-01T04:26:21Z","title":"Data Dwarfs: A Lens Towards Fully Understanding Big Data and AI Workloads"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00699","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c087c8016eb312e167c8b74bafabdc07531e5a37e3588053612202d99a10d154","target":"record","created_at":"2026-05-18T00:16:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"50c3a46cb1addd5cbd1d4c4d375130240fb63ab3f20dbff3a42e645727685d03","cross_cats_sorted":["cs.PF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-01T04:26:21Z","title_canon_sha256":"4c2f872da26fe489cf40d23c10ab6507bcaab9614aee2264bf4fbdc3cc2d07e8"},"schema_version":"1.0","source":{"id":"1802.00699","kind":"arxiv","version":2}},"canonical_sha256":"994d80db132cc52dbe71b6944adcacd2493793cbcd0e69e8351c034587b14056","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"994d80db132cc52dbe71b6944adcacd2493793cbcd0e69e8351c034587b14056","first_computed_at":"2026-05-18T00:16:50.193641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:50.193641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iIF9UOBGoFo8/QPUhRzRebnMwanlfgohQ5eYGWPbOK/slwcRPA4nX05tT2mBqE7OkId4KpFn4GXCp2tg2KaEBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:50.194620Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.00699","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c087c8016eb312e167c8b74bafabdc07531e5a37e3588053612202d99a10d154","sha256:522bfed9d38d2ca7b89b024689d528ceeb2331f5b22a5f43b598d5495db6f254"],"state_sha256":"fb904c793794fe8c557f57b1b132ebfb71fcfa2db80fb07856d7503d37253aae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"su7aW9UWO2/xFwbNf7zdkwB1FpxN2VEPN2b2lkww3zD5N7Hcu+irXBaE13cGbZl3Mzaa/6lzLxJeggDi+FVrBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T14:48:28.070905Z","bundle_sha256":"e0a734b7f96a44a7240cb611d12ea247341818934b48a92251ed55cd3eac88f1"}}