{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6UUARVR2X5CYDID6P37WJ4WL5N","short_pith_number":"pith:6UUARVR2","canonical_record":{"source":{"id":"2108.05053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T06:36:57Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"b2283df28c7b66308cac7b46945852a5bda2a5f47fbe29226b67f0c1066865b2","abstract_canon_sha256":"8ed51b72b5215df9b69daff7cdbc2f88352ea748d07d30eb7d0303fd219f2613"},"schema_version":"1.0"},"canonical_sha256":"f52808d63abf4581a07e7eff64f2cbeb4e3ab87394b4f5d0feffc175242a4acd","source":{"kind":"arxiv","id":"2108.05053","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05053","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05053v1","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05053","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"6UUARVR2X5CY","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"6UUARVR2X5CYDID6","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"6UUARVR2","created_at":"2026-07-05T03:05:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6UUARVR2X5CYDID6P37WJ4WL5N","target":"record","payload":{"canonical_record":{"source":{"id":"2108.05053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T06:36:57Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"b2283df28c7b66308cac7b46945852a5bda2a5f47fbe29226b67f0c1066865b2","abstract_canon_sha256":"8ed51b72b5215df9b69daff7cdbc2f88352ea748d07d30eb7d0303fd219f2613"},"schema_version":"1.0"},"canonical_sha256":"f52808d63abf4581a07e7eff64f2cbeb4e3ab87394b4f5d0feffc175242a4acd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:06.454936Z","signature_b64":"AeZG8RyfVA+v61+PwN+9IA4eBc/cVNto58Q9yVFbzoNYFJJeKrpiRxa7heVfPBM2m6xVEzHIffUTCXtoNt3xCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f52808d63abf4581a07e7eff64f2cbeb4e3ab87394b4f5d0feffc175242a4acd","last_reissued_at":"2026-07-05T03:05:06.454375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:06.454375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.05053","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32S1lLeStq6P497/CtzPGAxUYOEPsKfECReY52ODvhcRe3MWywT9WDK6Di4tPv6KW5h2ejNPlndQQ57Me+eDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:32:24.323106Z"},"content_sha256":"037f1640292cefd3c66e738a4d2a7e08b3d58651c28e8fbdd028e5b70246b98d","schema_version":"1.0","event_id":"sha256:037f1640292cefd3c66e738a4d2a7e08b3d58651c28e8fbdd028e5b70246b98d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6UUARVR2X5CYDID6P37WJ4WL5N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Managing ML Pipelines: Feature Stores and the Coming Wave of Embedding Ecosystems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Atindriyo Sanyal, Karan Goel, Laurel Orr, Megan Leszczynski, Xiao Ling","submitted_at":"2021-08-11T06:36:57Z","abstract_excerpt":"The industrial machine learning pipeline requires iterating on model features, training and deploying models, and monitoring deployed models at scale. Feature stores were developed to manage and standardize the engineer's workflow in this end-to-end pipeline, focusing on traditional tabular feature data. In recent years, however, model development has shifted towards using self-supervised pretrained embeddings as model features. Managing these embeddings and the downstream systems that use them introduces new challenges with respect to managing embedding training data, measuring embedding qual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05053","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/2108.05053/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRfhqfNR/ETG7O346bH7li3C651XY2YkuICxzG96BMn/RPx0VZa3Qv0uqhg9d7y6dI+GgAeAgetpzjOiDnehCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:32:24.324039Z"},"content_sha256":"1b41df54b623b4bd5f4286d8a56b74e0f7a55aac989dd17da77f1a6fbb779a26","schema_version":"1.0","event_id":"sha256:1b41df54b623b4bd5f4286d8a56b74e0f7a55aac989dd17da77f1a6fbb779a26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UUARVR2X5CYDID6P37WJ4WL5N/bundle.json","state_url":"https://pith.science/pith/6UUARVR2X5CYDID6P37WJ4WL5N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UUARVR2X5CYDID6P37WJ4WL5N/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":"2026-08-11T05:32:24Z","links":{"resolver":"https://pith.science/pith/6UUARVR2X5CYDID6P37WJ4WL5N","bundle":"https://pith.science/pith/6UUARVR2X5CYDID6P37WJ4WL5N/bundle.json","state":"https://pith.science/pith/6UUARVR2X5CYDID6P37WJ4WL5N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UUARVR2X5CYDID6P37WJ4WL5N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6UUARVR2X5CYDID6P37WJ4WL5N","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":"8ed51b72b5215df9b69daff7cdbc2f88352ea748d07d30eb7d0303fd219f2613","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T06:36:57Z","title_canon_sha256":"b2283df28c7b66308cac7b46945852a5bda2a5f47fbe29226b67f0c1066865b2"},"schema_version":"1.0","source":{"id":"2108.05053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05053","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05053v1","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05053","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"6UUARVR2X5CY","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"6UUARVR2X5CYDID6","created_at":"2026-07-05T03:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"6UUARVR2","created_at":"2026-07-05T03:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:1b41df54b623b4bd5f4286d8a56b74e0f7a55aac989dd17da77f1a6fbb779a26","target":"graph","created_at":"2026-07-05T03:05:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.05053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The industrial machine learning pipeline requires iterating on model features, training and deploying models, and monitoring deployed models at scale. Feature stores were developed to manage and standardize the engineer's workflow in this end-to-end pipeline, focusing on traditional tabular feature data. In recent years, however, model development has shifted towards using self-supervised pretrained embeddings as model features. Managing these embeddings and the downstream systems that use them introduces new challenges with respect to managing embedding training data, measuring embedding qual","authors_text":"Atindriyo Sanyal, Karan Goel, Laurel Orr, Megan Leszczynski, Xiao Ling","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T06:36:57Z","title":"Managing ML Pipelines: Feature Stores and the Coming Wave of Embedding Ecosystems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05053","kind":"arxiv","version":1},"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":"sha256:037f1640292cefd3c66e738a4d2a7e08b3d58651c28e8fbdd028e5b70246b98d","target":"record","created_at":"2026-07-05T03:05:06Z","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":"8ed51b72b5215df9b69daff7cdbc2f88352ea748d07d30eb7d0303fd219f2613","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-11T06:36:57Z","title_canon_sha256":"b2283df28c7b66308cac7b46945852a5bda2a5f47fbe29226b67f0c1066865b2"},"schema_version":"1.0","source":{"id":"2108.05053","kind":"arxiv","version":1}},"canonical_sha256":"f52808d63abf4581a07e7eff64f2cbeb4e3ab87394b4f5d0feffc175242a4acd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f52808d63abf4581a07e7eff64f2cbeb4e3ab87394b4f5d0feffc175242a4acd","first_computed_at":"2026-07-05T03:05:06.454375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:06.454375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AeZG8RyfVA+v61+PwN+9IA4eBc/cVNto58Q9yVFbzoNYFJJeKrpiRxa7heVfPBM2m6xVEzHIffUTCXtoNt3xCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:06.454936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:037f1640292cefd3c66e738a4d2a7e08b3d58651c28e8fbdd028e5b70246b98d","sha256:1b41df54b623b4bd5f4286d8a56b74e0f7a55aac989dd17da77f1a6fbb779a26"],"state_sha256":"c3820ba02ff90b74e1ecb9d1e987df01ef21433684bcb8e31f6dcb77bc676220"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6Xi/daRVYBDPkyAvDbluE0B7OtYpRIRPXD1X3k/6ysE20BxGiG1wPfkYaEIiUVlVZfStOVUI+SC7qQofRUgCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:32:24.333805Z","bundle_sha256":"45bb26fc03e2b6fc6757530d876a52072941451089f872bf5c500457afda753f"}}