{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:4FUQZ4546GCAJNY4XDKCESRWCI","short_pith_number":"pith:4FUQZ454","canonical_record":{"source":{"id":"1206.5240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-20T14:52:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8d179755fd2b930c0aadc425210773ce61487d9284379f33dd761bba620e7965","abstract_canon_sha256":"ba5c33076dcb495f099f73621a24f617530419576feb4665e9317d87c56bcf48"},"schema_version":"1.0"},"canonical_sha256":"e1690cf3bcf18404b71cb8d4224a36120fdfc435cfd85d9704ecc3cd4a4cb527","source":{"kind":"arxiv","id":"1206.5240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5240","created_at":"2026-05-18T03:52:41Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5240v1","created_at":"2026-05-18T03:52:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5240","created_at":"2026-05-18T03:52:41Z"},{"alias_kind":"pith_short_12","alias_value":"4FUQZ4546GCA","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"4FUQZ4546GCAJNY4","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"4FUQZ454","created_at":"2026-05-18T12:26:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:4FUQZ4546GCAJNY4XDKCESRWCI","target":"record","payload":{"canonical_record":{"source":{"id":"1206.5240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-20T14:52:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8d179755fd2b930c0aadc425210773ce61487d9284379f33dd761bba620e7965","abstract_canon_sha256":"ba5c33076dcb495f099f73621a24f617530419576feb4665e9317d87c56bcf48"},"schema_version":"1.0"},"canonical_sha256":"e1690cf3bcf18404b71cb8d4224a36120fdfc435cfd85d9704ecc3cd4a4cb527","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:41.033105Z","signature_b64":"DnnnRMYhHPqSkbES46/iUk+Gh5JVi3TgdAiOU1MPzPS/e6dQghSo5dFZ8aBcZOwX6wWeE74vWieYvF+yKlkOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1690cf3bcf18404b71cb8d4224a36120fdfc435cfd85d9704ecc3cd4a4cb527","last_reissued_at":"2026-05-18T03:52:41.032614Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:41.032614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.5240","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":"2026-05-18T03:52:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TUtkLDLOgkXn9TIUJMisshsJwAV4uIRrw1fPSeJP+1OfcZJCIEppMKV2lJLZX9m+A1YdOFAQwCq8ke48ORoPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T05:13:19.102191Z"},"content_sha256":"341f9178771077bed0abc1216807b5b4fb87bf742dc2ed3ee664a4997760dc61","schema_version":"1.0","event_id":"sha256:341f9178771077bed0abc1216807b5b4fb87bf742dc2ed3ee664a4997760dc61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:4FUQZ4546GCAJNY4XDKCESRWCI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analysis of Semi-Supervised Learning with the Yarowsky Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anoop Sarkar, Gholam Reza Haffari","submitted_at":"2012-06-20T14:52:04Z","abstract_excerpt":"The Yarowsky algorithm is a rule-based semi-supervised learning algorithm that has been successfully applied to some problems in computational linguistics. The algorithm was not mathematically well understood until (Abney 2004) which analyzed some specific variants of the algorithm, and also proposed some new algorithms for bootstrapping. In this paper, we extend Abney's work and show that some of his proposed algorithms actually optimize (an upper-bound on) an objective function based on a new definition of cross-entropy which is based on a particular instantiation of the Bregman distance bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5240","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":""},"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":"2026-05-18T03:52:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z7/7EATz1RqIBeH+wsMV0DaA9DEuoAqiSrRjY8qMCMfY1eKfEUQDCMPFu6UIlEknAUCk2bUq3qSYIhHNkYszBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T05:13:19.102879Z"},"content_sha256":"bb138c018b7e9a560def84f19d6a689a3cb6bbff772fa069f175dbc241f32d9b","schema_version":"1.0","event_id":"sha256:bb138c018b7e9a560def84f19d6a689a3cb6bbff772fa069f175dbc241f32d9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FUQZ4546GCAJNY4XDKCESRWCI/bundle.json","state_url":"https://pith.science/pith/4FUQZ4546GCAJNY4XDKCESRWCI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FUQZ4546GCAJNY4XDKCESRWCI/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":"2026-06-25T05:13:19Z","links":{"resolver":"https://pith.science/pith/4FUQZ4546GCAJNY4XDKCESRWCI","bundle":"https://pith.science/pith/4FUQZ4546GCAJNY4XDKCESRWCI/bundle.json","state":"https://pith.science/pith/4FUQZ4546GCAJNY4XDKCESRWCI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FUQZ4546GCAJNY4XDKCESRWCI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:4FUQZ4546GCAJNY4XDKCESRWCI","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":"ba5c33076dcb495f099f73621a24f617530419576feb4665e9317d87c56bcf48","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-20T14:52:04Z","title_canon_sha256":"8d179755fd2b930c0aadc425210773ce61487d9284379f33dd761bba620e7965"},"schema_version":"1.0","source":{"id":"1206.5240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5240","created_at":"2026-05-18T03:52:41Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5240v1","created_at":"2026-05-18T03:52:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5240","created_at":"2026-05-18T03:52:41Z"},{"alias_kind":"pith_short_12","alias_value":"4FUQZ4546GCA","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"4FUQZ4546GCAJNY4","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"4FUQZ454","created_at":"2026-05-18T12:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:bb138c018b7e9a560def84f19d6a689a3cb6bbff772fa069f175dbc241f32d9b","target":"graph","created_at":"2026-05-18T03:52:41Z","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 Yarowsky algorithm is a rule-based semi-supervised learning algorithm that has been successfully applied to some problems in computational linguistics. The algorithm was not mathematically well understood until (Abney 2004) which analyzed some specific variants of the algorithm, and also proposed some new algorithms for bootstrapping. In this paper, we extend Abney's work and show that some of his proposed algorithms actually optimize (an upper-bound on) an objective function based on a new definition of cross-entropy which is based on a particular instantiation of the Bregman distance bet","authors_text":"Anoop Sarkar, Gholam Reza Haffari","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-20T14:52:04Z","title":"Analysis of Semi-Supervised Learning with the Yarowsky Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5240","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":"sha256:341f9178771077bed0abc1216807b5b4fb87bf742dc2ed3ee664a4997760dc61","target":"record","created_at":"2026-05-18T03:52:41Z","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":"ba5c33076dcb495f099f73621a24f617530419576feb4665e9317d87c56bcf48","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-20T14:52:04Z","title_canon_sha256":"8d179755fd2b930c0aadc425210773ce61487d9284379f33dd761bba620e7965"},"schema_version":"1.0","source":{"id":"1206.5240","kind":"arxiv","version":1}},"canonical_sha256":"e1690cf3bcf18404b71cb8d4224a36120fdfc435cfd85d9704ecc3cd4a4cb527","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1690cf3bcf18404b71cb8d4224a36120fdfc435cfd85d9704ecc3cd4a4cb527","first_computed_at":"2026-05-18T03:52:41.032614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:41.032614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DnnnRMYhHPqSkbES46/iUk+Gh5JVi3TgdAiOU1MPzPS/e6dQghSo5dFZ8aBcZOwX6wWeE74vWieYvF+yKlkOBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:41.033105Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.5240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:341f9178771077bed0abc1216807b5b4fb87bf742dc2ed3ee664a4997760dc61","sha256:bb138c018b7e9a560def84f19d6a689a3cb6bbff772fa069f175dbc241f32d9b"],"state_sha256":"23c2571055a2c3ea151e7776c7588f75a0455577515e824a835af66be9ca0a5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UGTWs+CXF5Fh5iWEq1SzKD5+HX9+Uu1STOoeAaespCVqlGhQ8N11E22Cx7bLnF8v928dLNOC9VXQ2gPNirwsBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T05:13:19.106011Z","bundle_sha256":"e6ede8f35af5d6833d22785e04d2bb9dc7e77c6814a3a935c2992ae1fad765d6"}}