{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OMWUCIM2WV4DABZWQYOT3OZAYB","short_pith_number":"pith:OMWUCIM2","canonical_record":{"source":{"id":"1709.08600","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-25T17:10:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b13b2288f0087e2b3135a90b56382dfbc01db40b1fa604ba6eba3fea4661b887","abstract_canon_sha256":"1d96f30f6818e8653d8bf86dbe7cc35111b00dd3773654daa303210dd1feeaa2"},"schema_version":"1.0"},"canonical_sha256":"732d41219ab578300736861d3dbb20c07b71b5ddf6c35370207c6d0e5d22cbcb","source":{"kind":"arxiv","id":"1709.08600","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.08600","created_at":"2026-05-18T00:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"1709.08600v3","created_at":"2026-05-18T00:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08600","created_at":"2026-05-18T00:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"OMWUCIM2WV4D","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OMWUCIM2WV4DABZW","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OMWUCIM2","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OMWUCIM2WV4DABZWQYOT3OZAYB","target":"record","payload":{"canonical_record":{"source":{"id":"1709.08600","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-25T17:10:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b13b2288f0087e2b3135a90b56382dfbc01db40b1fa604ba6eba3fea4661b887","abstract_canon_sha256":"1d96f30f6818e8653d8bf86dbe7cc35111b00dd3773654daa303210dd1feeaa2"},"schema_version":"1.0"},"canonical_sha256":"732d41219ab578300736861d3dbb20c07b71b5ddf6c35370207c6d0e5d22cbcb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:57.906134Z","signature_b64":"Rgf9zIEFrLxfELs6MJUfbj4G3aELjUbSwd1TKyCEUG/FNQane4q6DMBFy9AKOC/DEB6zp2hA8W6x7iTsI0apDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"732d41219ab578300736861d3dbb20c07b71b5ddf6c35370207c6d0e5d22cbcb","last_reissued_at":"2026-05-18T00:11:57.905489Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:57.905489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.08600","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbF1psfZkkDtyce8eAW0JZmIG7yXitANkS9wWtZzM7Sq41Jm1Pwd4L8POKJqjRt8E+Ko7X5EhtdoTj8fsaWfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T03:55:29.169397Z"},"content_sha256":"1df215f90a902e3d1e77f582930533e79e0deaa261588bf7a3c6fe84054cfc6a","schema_version":"1.0","event_id":"sha256:1df215f90a902e3d1e77f582930533e79e0deaa261588bf7a3c6fe84054cfc6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OMWUCIM2WV4DABZWQYOT3OZAYB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EZLearn: Exploiting Organic Supervision in Large-Scale Data Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bill Howe, Hoifung Poon, Maxim Grechkin","submitted_at":"2017-09-25T17:10:46Z","abstract_excerpt":"Many real-world applications require automated data annotation, such as identifying tissue origins based on gene expressions and classifying images into semantic categories. Annotation classes are often numerous and subject to changes over time, and annotating examples has become the major bottleneck for supervised learning methods. In science and other high-value domains, large repositories of data samples are often available, together with two sources of organic supervision: a lexicon for the annotation classes, and text descriptions that accompany some data samples. Distant supervision has "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08600","kind":"arxiv","version":3},"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":"2026-05-18T00:11:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jDKMkxwOsGXBOutYY9aFxBgOj+8NUhEul9S4BKcNcmmMs5TZz6YG6ZnHltAhwkuGVBLe34tId4sBpEVDPeAsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T03:55:29.170033Z"},"content_sha256":"2724291a07d9281989dfc01a571f264a611e448b97250eb623a6bcb8d8e2c178","schema_version":"1.0","event_id":"sha256:2724291a07d9281989dfc01a571f264a611e448b97250eb623a6bcb8d8e2c178"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMWUCIM2WV4DABZWQYOT3OZAYB/bundle.json","state_url":"https://pith.science/pith/OMWUCIM2WV4DABZWQYOT3OZAYB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMWUCIM2WV4DABZWQYOT3OZAYB/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":"2026-06-06T03:55:29Z","links":{"resolver":"https://pith.science/pith/OMWUCIM2WV4DABZWQYOT3OZAYB","bundle":"https://pith.science/pith/OMWUCIM2WV4DABZWQYOT3OZAYB/bundle.json","state":"https://pith.science/pith/OMWUCIM2WV4DABZWQYOT3OZAYB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMWUCIM2WV4DABZWQYOT3OZAYB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OMWUCIM2WV4DABZWQYOT3OZAYB","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":"1d96f30f6818e8653d8bf86dbe7cc35111b00dd3773654daa303210dd1feeaa2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-25T17:10:46Z","title_canon_sha256":"b13b2288f0087e2b3135a90b56382dfbc01db40b1fa604ba6eba3fea4661b887"},"schema_version":"1.0","source":{"id":"1709.08600","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.08600","created_at":"2026-05-18T00:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"1709.08600v3","created_at":"2026-05-18T00:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08600","created_at":"2026-05-18T00:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"OMWUCIM2WV4D","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OMWUCIM2WV4DABZW","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OMWUCIM2","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:2724291a07d9281989dfc01a571f264a611e448b97250eb623a6bcb8d8e2c178","target":"graph","created_at":"2026-05-18T00:11:57Z","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":"Many real-world applications require automated data annotation, such as identifying tissue origins based on gene expressions and classifying images into semantic categories. Annotation classes are often numerous and subject to changes over time, and annotating examples has become the major bottleneck for supervised learning methods. In science and other high-value domains, large repositories of data samples are often available, together with two sources of organic supervision: a lexicon for the annotation classes, and text descriptions that accompany some data samples. Distant supervision has ","authors_text":"Bill Howe, Hoifung Poon, Maxim Grechkin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-25T17:10:46Z","title":"EZLearn: Exploiting Organic Supervision in Large-Scale Data Annotation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08600","kind":"arxiv","version":3},"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":"sha256:1df215f90a902e3d1e77f582930533e79e0deaa261588bf7a3c6fe84054cfc6a","target":"record","created_at":"2026-05-18T00:11:57Z","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":"1d96f30f6818e8653d8bf86dbe7cc35111b00dd3773654daa303210dd1feeaa2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-25T17:10:46Z","title_canon_sha256":"b13b2288f0087e2b3135a90b56382dfbc01db40b1fa604ba6eba3fea4661b887"},"schema_version":"1.0","source":{"id":"1709.08600","kind":"arxiv","version":3}},"canonical_sha256":"732d41219ab578300736861d3dbb20c07b71b5ddf6c35370207c6d0e5d22cbcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"732d41219ab578300736861d3dbb20c07b71b5ddf6c35370207c6d0e5d22cbcb","first_computed_at":"2026-05-18T00:11:57.905489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:57.905489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rgf9zIEFrLxfELs6MJUfbj4G3aELjUbSwd1TKyCEUG/FNQane4q6DMBFy9AKOC/DEB6zp2hA8W6x7iTsI0apDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:57.906134Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.08600","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1df215f90a902e3d1e77f582930533e79e0deaa261588bf7a3c6fe84054cfc6a","sha256:2724291a07d9281989dfc01a571f264a611e448b97250eb623a6bcb8d8e2c178"],"state_sha256":"9a92dcdf69643d5dcc3fada0835f4f10376bb2db936a4ea1fc28e6ad1b589ea8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6aKaBLRKLwiwcXN3jCfR1YRF2xfpK0F1VuqLYe2O/txxoc2ufS/quUhLWJHUTTOZysNdUKnBQH4vQgJxoh+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T03:55:29.173390Z","bundle_sha256":"bd707f901f0e4b8fb114bd6372634d266d687589c5d70af62ab6384048eb3b63"}}