{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KHFDKAIHI32NODLDADLFUJSUCN","short_pith_number":"pith:KHFDKAIH","canonical_record":{"source":{"id":"2205.09067","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T16:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"ec44d7f7599342e54ed77aeda01bd048eba5b279a6b46199e42562083c73e63a","abstract_canon_sha256":"82fe8a661a83f4adf1a8c795afa549246c6fd0023653a349bc7d4ab254ef570f"},"schema_version":"1.0"},"canonical_sha256":"51ca35010746f4d70d6300d65a2654135a0913c2e4c4abe322695e141a68f13f","source":{"kind":"arxiv","id":"2205.09067","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09067","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09067v5","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09067","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"KHFDKAIHI32N","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"KHFDKAIHI32NODLD","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"KHFDKAIH","created_at":"2026-07-05T05:06:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KHFDKAIHI32NODLDADLFUJSUCN","target":"record","payload":{"canonical_record":{"source":{"id":"2205.09067","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T16:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"ec44d7f7599342e54ed77aeda01bd048eba5b279a6b46199e42562083c73e63a","abstract_canon_sha256":"82fe8a661a83f4adf1a8c795afa549246c6fd0023653a349bc7d4ab254ef570f"},"schema_version":"1.0"},"canonical_sha256":"51ca35010746f4d70d6300d65a2654135a0913c2e4c4abe322695e141a68f13f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:31.372181Z","signature_b64":"7kqb13GzU7+xYIzukA0kc2ZX5aOtma7FIhMik3kfx4V9EIeWOMrcvIwdyYZd0ijhFCJddlWw6h2JkIYuoYhJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51ca35010746f4d70d6300d65a2654135a0913c2e4c4abe322695e141a68f13f","last_reissued_at":"2026-07-05T05:06:31.371740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:31.371740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.09067","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JGeerm700FjRhLb+VJvMV3TuAsy0p97uN9zAxNRlTwUpewMe3HQlwzR+yutEJdoAl4XLQygdaWFrp785gGVQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:49:36.031542Z"},"content_sha256":"f0b70f611a49ff0e449afb578ec182838933450a075e5ce9a84cb3d7bf713da4","schema_version":"1.0","event_id":"sha256:f0b70f611a49ff0e449afb578ec182838933450a075e5ce9a84cb3d7bf713da4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KHFDKAIHI32NODLDADLFUJSUCN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Rule Induction for Interpretable Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Michael Zeng, Reid Pryzant, Yichong Xu, Ziyi Yang","submitted_at":"2022-05-18T16:50:20Z","abstract_excerpt":"Semi-supervised learning has shown promise in allowing NLP models to generalize from small amounts of labeled data. Meanwhile, pretrained transformer models act as black-box correlation engines that are difficult to explain and sometimes behave unreliably. In this paper, we propose tackling both of these challenges via Automatic Rule Induction (ARI), a simple and general-purpose framework for the automatic discovery and integration of symbolic rules into pretrained transformer models. First, we extract weak symbolic rules from low-capacity machine learning models trained on small amounts of la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09067","kind":"arxiv","version":5},"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/2205.09067/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":"2026-07-05T05:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/6tdu9g68ygyZkoSGXy0dUtZWKID0ZxjRJqIE6iwA4fKmg7J9ppummF1hiKbBkHuIUAeXvOzYrLDIdKQUl1hAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:49:36.032050Z"},"content_sha256":"48776ded44aaec9d8884ce6a1a3bd67b69e275ee562ce51577a53da8808b35af","schema_version":"1.0","event_id":"sha256:48776ded44aaec9d8884ce6a1a3bd67b69e275ee562ce51577a53da8808b35af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHFDKAIHI32NODLDADLFUJSUCN/bundle.json","state_url":"https://pith.science/pith/KHFDKAIHI32NODLDADLFUJSUCN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHFDKAIHI32NODLDADLFUJSUCN/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":"2026-08-06T09:49:36Z","links":{"resolver":"https://pith.science/pith/KHFDKAIHI32NODLDADLFUJSUCN","bundle":"https://pith.science/pith/KHFDKAIHI32NODLDADLFUJSUCN/bundle.json","state":"https://pith.science/pith/KHFDKAIHI32NODLDADLFUJSUCN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHFDKAIHI32NODLDADLFUJSUCN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KHFDKAIHI32NODLDADLFUJSUCN","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":"82fe8a661a83f4adf1a8c795afa549246c6fd0023653a349bc7d4ab254ef570f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T16:50:20Z","title_canon_sha256":"ec44d7f7599342e54ed77aeda01bd048eba5b279a6b46199e42562083c73e63a"},"schema_version":"1.0","source":{"id":"2205.09067","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09067","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09067v5","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09067","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"KHFDKAIHI32N","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"KHFDKAIHI32NODLD","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"KHFDKAIH","created_at":"2026-07-05T05:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:48776ded44aaec9d8884ce6a1a3bd67b69e275ee562ce51577a53da8808b35af","target":"graph","created_at":"2026-07-05T05:06:31Z","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/2205.09067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semi-supervised learning has shown promise in allowing NLP models to generalize from small amounts of labeled data. Meanwhile, pretrained transformer models act as black-box correlation engines that are difficult to explain and sometimes behave unreliably. In this paper, we propose tackling both of these challenges via Automatic Rule Induction (ARI), a simple and general-purpose framework for the automatic discovery and integration of symbolic rules into pretrained transformer models. First, we extract weak symbolic rules from low-capacity machine learning models trained on small amounts of la","authors_text":"Chenguang Zhu, Michael Zeng, Reid Pryzant, Yichong Xu, Ziyi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T16:50:20Z","title":"Automatic Rule Induction for Interpretable Semi-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09067","kind":"arxiv","version":5},"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:f0b70f611a49ff0e449afb578ec182838933450a075e5ce9a84cb3d7bf713da4","target":"record","created_at":"2026-07-05T05:06:31Z","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":"82fe8a661a83f4adf1a8c795afa549246c6fd0023653a349bc7d4ab254ef570f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T16:50:20Z","title_canon_sha256":"ec44d7f7599342e54ed77aeda01bd048eba5b279a6b46199e42562083c73e63a"},"schema_version":"1.0","source":{"id":"2205.09067","kind":"arxiv","version":5}},"canonical_sha256":"51ca35010746f4d70d6300d65a2654135a0913c2e4c4abe322695e141a68f13f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51ca35010746f4d70d6300d65a2654135a0913c2e4c4abe322695e141a68f13f","first_computed_at":"2026-07-05T05:06:31.371740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:31.371740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7kqb13GzU7+xYIzukA0kc2ZX5aOtma7FIhMik3kfx4V9EIeWOMrcvIwdyYZd0ijhFCJddlWw6h2JkIYuoYhJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:31.372181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.09067","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0b70f611a49ff0e449afb578ec182838933450a075e5ce9a84cb3d7bf713da4","sha256:48776ded44aaec9d8884ce6a1a3bd67b69e275ee562ce51577a53da8808b35af"],"state_sha256":"bc6e86003ab4811004919d572ef8dc2641c891911c5475af46bc86436c6ba7b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OJEDVcKP7oIQuWLfpV2zvup3EVOYJav/Ba/nqCI3QuKlhCHMEfdS8/gWndWjndA+PCFa6MlpacdWM8YxtvlUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:49:36.036652Z","bundle_sha256":"092dca9606825fdb5dba254c820f13434184d8eefc354d4385318000d035495b"}}