{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QTVBZ6NC25M27GOPFR6KNG5MZ7","short_pith_number":"pith:QTVBZ6NC","canonical_record":{"source":{"id":"2210.00987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T14:53:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5656bd4abd82195f7794773b79ef3853b9b6fce7d27a0b584909556909439abc","abstract_canon_sha256":"e1bb9761c474325275f62c2a13fb7ee1211a2ac90a0cb432266c9cb30e6b92ef"},"schema_version":"1.0"},"canonical_sha256":"84ea1cf9a2d759af99cf2c7ca69baccffff4f78e8476bb3d1e542ed6618907d8","source":{"kind":"arxiv","id":"2210.00987","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.00987","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"2210.00987v1","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00987","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"QTVBZ6NC25M2","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"pith_short_16","alias_value":"QTVBZ6NC25M27GOP","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"pith_short_8","alias_value":"QTVBZ6NC","created_at":"2026-07-05T05:02:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QTVBZ6NC25M27GOPFR6KNG5MZ7","target":"record","payload":{"canonical_record":{"source":{"id":"2210.00987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T14:53:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5656bd4abd82195f7794773b79ef3853b9b6fce7d27a0b584909556909439abc","abstract_canon_sha256":"e1bb9761c474325275f62c2a13fb7ee1211a2ac90a0cb432266c9cb30e6b92ef"},"schema_version":"1.0"},"canonical_sha256":"84ea1cf9a2d759af99cf2c7ca69baccffff4f78e8476bb3d1e542ed6618907d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:49.944767Z","signature_b64":"9sYqFuJ7SmOj4cxm21wDrgn/e730VANom9qZU7tBfKHi8PvVgITJdyFqVVkVfPivPJEbY/syImP30i9KzHPBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ea1cf9a2d759af99cf2c7ca69baccffff4f78e8476bb3d1e542ed6618907d8","last_reissued_at":"2026-07-05T05:02:49.944331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:49.944331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.00987","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":"2026-07-05T05:02:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"spO+tc/WKmFHoxdgiA/maHITGW9lrSlunv30TmFhn9QFrAeB+WaflhUybcKW4W1Lkj3eqWCSg1yqZACG4PA2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:28:46.365520Z"},"content_sha256":"07c9bf4f21ced1bc4dd0beca9039d7ed38e192ac07adae9f90600304b3b1f538","schema_version":"1.0","event_id":"sha256:07c9bf4f21ced1bc4dd0beca9039d7ed38e192ac07adae9f90600304b3b1f538"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QTVBZ6NC25M27GOPFR6KNG5MZ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Budgeting for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"James Zou, Weixin Liang, Xinyi Zhao","submitted_at":"2022-10-03T14:53:17Z","abstract_excerpt":"Data is the fuel powering AI and creates tremendous value for many domains. However, collecting datasets for AI is a time-consuming, expensive, and complicated endeavor. For practitioners, data investment remains to be a leap of faith in practice. In this work, we study the data budgeting problem and formulate it as two sub-problems: predicting (1) what is the saturating performance if given enough data, and (2) how many data points are needed to reach near the saturating performance. Different from traditional dataset-independent methods like PowerLaw, we proposed a learning method to solve d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00987","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/2210.00987/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":"2026-07-05T05:02:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uh522tMcNIC2yzxK1H6lrd4uVClJE1r22EeVYLQ7TSpRBRxePS++QG+yNPv14bkWEYB3icIO5BjhfIXvUw0DCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:28:46.366029Z"},"content_sha256":"ad4d8d28aa22980eca30d43d7b1824ad71b8d04c32ffddc0f8c109745c972647","schema_version":"1.0","event_id":"sha256:ad4d8d28aa22980eca30d43d7b1824ad71b8d04c32ffddc0f8c109745c972647"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/bundle.json","state_url":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/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":"2026-08-14T09:28:46Z","links":{"resolver":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7","bundle":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/bundle.json","state":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QTVBZ6NC25M27GOPFR6KNG5MZ7","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":"e1bb9761c474325275f62c2a13fb7ee1211a2ac90a0cb432266c9cb30e6b92ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T14:53:17Z","title_canon_sha256":"5656bd4abd82195f7794773b79ef3853b9b6fce7d27a0b584909556909439abc"},"schema_version":"1.0","source":{"id":"2210.00987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.00987","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"2210.00987v1","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00987","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"QTVBZ6NC25M2","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"pith_short_16","alias_value":"QTVBZ6NC25M27GOP","created_at":"2026-07-05T05:02:49Z"},{"alias_kind":"pith_short_8","alias_value":"QTVBZ6NC","created_at":"2026-07-05T05:02:49Z"}],"graph_snapshots":[{"event_id":"sha256:ad4d8d28aa22980eca30d43d7b1824ad71b8d04c32ffddc0f8c109745c972647","target":"graph","created_at":"2026-07-05T05:02:49Z","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/2210.00987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data is the fuel powering AI and creates tremendous value for many domains. However, collecting datasets for AI is a time-consuming, expensive, and complicated endeavor. For practitioners, data investment remains to be a leap of faith in practice. In this work, we study the data budgeting problem and formulate it as two sub-problems: predicting (1) what is the saturating performance if given enough data, and (2) how many data points are needed to reach near the saturating performance. Different from traditional dataset-independent methods like PowerLaw, we proposed a learning method to solve d","authors_text":"James Zou, Weixin Liang, Xinyi Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T14:53:17Z","title":"Data Budgeting for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00987","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":"sha256:07c9bf4f21ced1bc4dd0beca9039d7ed38e192ac07adae9f90600304b3b1f538","target":"record","created_at":"2026-07-05T05:02:49Z","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":"e1bb9761c474325275f62c2a13fb7ee1211a2ac90a0cb432266c9cb30e6b92ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T14:53:17Z","title_canon_sha256":"5656bd4abd82195f7794773b79ef3853b9b6fce7d27a0b584909556909439abc"},"schema_version":"1.0","source":{"id":"2210.00987","kind":"arxiv","version":1}},"canonical_sha256":"84ea1cf9a2d759af99cf2c7ca69baccffff4f78e8476bb3d1e542ed6618907d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84ea1cf9a2d759af99cf2c7ca69baccffff4f78e8476bb3d1e542ed6618907d8","first_computed_at":"2026-07-05T05:02:49.944331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:49.944331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9sYqFuJ7SmOj4cxm21wDrgn/e730VANom9qZU7tBfKHi8PvVgITJdyFqVVkVfPivPJEbY/syImP30i9KzHPBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:49.944767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.00987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07c9bf4f21ced1bc4dd0beca9039d7ed38e192ac07adae9f90600304b3b1f538","sha256:ad4d8d28aa22980eca30d43d7b1824ad71b8d04c32ffddc0f8c109745c972647"],"state_sha256":"a7bf10a6725a60bd008107507ff7048dfc456a5d079d40e63eab20ac67191e69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHFTtdiBj0RNtluMYHnOolYGl6ozDFZ+dncJuL3IOS6TpoXyzuhUXzxAQ2k67aTW+tL7M986zUJFabjbU6fzAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:28:46.370129Z","bundle_sha256":"c76d658666831dc5ed149f1039292ae42d1bead550fba3fb4938be4620a0db29"}}