{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:COO4C4IG7QAWKWLN54FETXI36T","short_pith_number":"pith:COO4C4IG","canonical_record":{"source":{"id":"2110.08355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T20:37:29Z","cross_cats_sorted":[],"title_canon_sha256":"23955420c24d2ae44bb1ffbcdc427e156d6bf7981679961432e9eb7ed97c5f31","abstract_canon_sha256":"a375e63f86759239ce62f3c4e12eddba39bcbc75dac8abb54b52d4ed8eb6249a"},"schema_version":"1.0"},"canonical_sha256":"139dc17106fc0165596def0a49dd1bf4f557f774f46fddd1ad6a8012eeba761e","source":{"kind":"arxiv","id":"2110.08355","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08355","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08355v2","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08355","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_12","alias_value":"COO4C4IG7QAW","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"COO4C4IG7QAWKWLN","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"COO4C4IG","created_at":"2026-07-05T04:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:COO4C4IG7QAWKWLN54FETXI36T","target":"record","payload":{"canonical_record":{"source":{"id":"2110.08355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T20:37:29Z","cross_cats_sorted":[],"title_canon_sha256":"23955420c24d2ae44bb1ffbcdc427e156d6bf7981679961432e9eb7ed97c5f31","abstract_canon_sha256":"a375e63f86759239ce62f3c4e12eddba39bcbc75dac8abb54b52d4ed8eb6249a"},"schema_version":"1.0"},"canonical_sha256":"139dc17106fc0165596def0a49dd1bf4f557f774f46fddd1ad6a8012eeba761e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:53.451481Z","signature_b64":"7ED4wPprj1+hIjH9JBJu2v7sS7MvqHDWzujhLLO3wKorS5uAP+DJD5/cDWoUtQoj6+/kpOFBZVboETqLP11BBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"139dc17106fc0165596def0a49dd1bf4f557f774f46fddd1ad6a8012eeba761e","last_reissued_at":"2026-07-05T04:30:53.451042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:53.451042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.08355","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":"2026-07-05T04:30:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VSYZmJs+SNNwDtxuIzozSbFPwXFlPR6ly6TueZWmguu7mhBF5VJ2bthpDSuk4z/suS1BS0XDW2X2zXNN+BASDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:16:31.263234Z"},"content_sha256":"f15ea3a9e857650702ef346d81aff54e491177fad133ce3e6ea2593562a5eaa6","schema_version":"1.0","event_id":"sha256:f15ea3a9e857650702ef346d81aff54e491177fad133ce3e6ea2593562a5eaa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:COO4C4IG7QAWKWLN54FETXI36T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clean or Annotate: How to Spend a Limited Data Collection Budget","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek Chen, Samuel R. Bowman, Zhou Yu","submitted_at":"2021-10-15T20:37:29Z","abstract_excerpt":"Crowdsourcing platforms are often used to collect datasets for training machine learning models, despite higher levels of inaccurate labeling compared to expert labeling. There are two common strategies to manage the impact of such noise. The first involves aggregating redundant annotations, but comes at the expense of labeling substantially fewer examples. Secondly, prior works have also considered using the entire annotation budget to label as many examples as possible and subsequently apply denoising algorithms to implicitly clean the dataset. We find a middle ground and propose an approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08355","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/2110.08355/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":"2026-07-05T04:30:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXhcmWGPdVH1p1yxGZXWm67QtS/aq0XXKTpl7g1wxO4G5BG/CaMsIBT7//bfDloMwtHDiL78v5a9U+7ooCt7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:16:31.263731Z"},"content_sha256":"dbab6713c56d41de9fd8587186c040093b13e945d18567ab2eb4e2d8518f8ab0","schema_version":"1.0","event_id":"sha256:dbab6713c56d41de9fd8587186c040093b13e945d18567ab2eb4e2d8518f8ab0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/COO4C4IG7QAWKWLN54FETXI36T/bundle.json","state_url":"https://pith.science/pith/COO4C4IG7QAWKWLN54FETXI36T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/COO4C4IG7QAWKWLN54FETXI36T/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":"2026-08-19T22:16:31Z","links":{"resolver":"https://pith.science/pith/COO4C4IG7QAWKWLN54FETXI36T","bundle":"https://pith.science/pith/COO4C4IG7QAWKWLN54FETXI36T/bundle.json","state":"https://pith.science/pith/COO4C4IG7QAWKWLN54FETXI36T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/COO4C4IG7QAWKWLN54FETXI36T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:COO4C4IG7QAWKWLN54FETXI36T","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":"a375e63f86759239ce62f3c4e12eddba39bcbc75dac8abb54b52d4ed8eb6249a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T20:37:29Z","title_canon_sha256":"23955420c24d2ae44bb1ffbcdc427e156d6bf7981679961432e9eb7ed97c5f31"},"schema_version":"1.0","source":{"id":"2110.08355","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08355","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08355v2","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08355","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_12","alias_value":"COO4C4IG7QAW","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"COO4C4IG7QAWKWLN","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"COO4C4IG","created_at":"2026-07-05T04:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:dbab6713c56d41de9fd8587186c040093b13e945d18567ab2eb4e2d8518f8ab0","target":"graph","created_at":"2026-07-05T04:30:53Z","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/2110.08355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Crowdsourcing platforms are often used to collect datasets for training machine learning models, despite higher levels of inaccurate labeling compared to expert labeling. There are two common strategies to manage the impact of such noise. The first involves aggregating redundant annotations, but comes at the expense of labeling substantially fewer examples. Secondly, prior works have also considered using the entire annotation budget to label as many examples as possible and subsequently apply denoising algorithms to implicitly clean the dataset. We find a middle ground and propose an approach","authors_text":"Derek Chen, Samuel R. Bowman, Zhou Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T20:37:29Z","title":"Clean or Annotate: How to Spend a Limited Data Collection Budget"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08355","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:f15ea3a9e857650702ef346d81aff54e491177fad133ce3e6ea2593562a5eaa6","target":"record","created_at":"2026-07-05T04:30:53Z","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":"a375e63f86759239ce62f3c4e12eddba39bcbc75dac8abb54b52d4ed8eb6249a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T20:37:29Z","title_canon_sha256":"23955420c24d2ae44bb1ffbcdc427e156d6bf7981679961432e9eb7ed97c5f31"},"schema_version":"1.0","source":{"id":"2110.08355","kind":"arxiv","version":2}},"canonical_sha256":"139dc17106fc0165596def0a49dd1bf4f557f774f46fddd1ad6a8012eeba761e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"139dc17106fc0165596def0a49dd1bf4f557f774f46fddd1ad6a8012eeba761e","first_computed_at":"2026-07-05T04:30:53.451042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:53.451042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7ED4wPprj1+hIjH9JBJu2v7sS7MvqHDWzujhLLO3wKorS5uAP+DJD5/cDWoUtQoj6+/kpOFBZVboETqLP11BBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:53.451481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08355","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f15ea3a9e857650702ef346d81aff54e491177fad133ce3e6ea2593562a5eaa6","sha256:dbab6713c56d41de9fd8587186c040093b13e945d18567ab2eb4e2d8518f8ab0"],"state_sha256":"ee8251b2beac45e0e573addbe32809d3ef7cd1080181fe0eb3baa3f436429567"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBCZv343bK8oP2/8NOyYw6RObgTL1XplsQ1qRAXR7jx7jlVkYIzswbI5SLlx/ZREgDaENGNTfuNng24w/aHjAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:16:31.267735Z","bundle_sha256":"19065e24636a65c130ba0f619cf76e1e86f1ec243eaca5b01cb2b212a33bb9d7"}}