{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C3LF7NXLM34T2VHRO7FXXRWSVD","short_pith_number":"pith:C3LF7NXL","schema_version":"1.0","canonical_sha256":"16d65fb6eb66f93d54f177cb7bc6d2a8d550f4fc4d0804171fb2849cdb9cc003","source":{"kind":"arxiv","id":"2208.00335","version":5},"attestation_state":"computed","paper":{"title":"Rule Extraction in Machine Learning: Chat Incremental Pattern Constructor","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"ChatIPC extracts ordered token-transition rules from text and builds responses by similarity selection on a token graph.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caleb Princewill Nwokocha","submitted_at":"2022-07-31T01:52:40Z","abstract_excerpt":"Rule extraction is a central problem in interpretable machine learning because it seeks to convert opaque predictive behavior into human-readable symbolic structure. This paper presents Chat Incremental Pattern Constructor (ChatIPC), a lightweight incremental symbolic learning system that extracts ordered token-transition rules from text, enriches them with definition-based expansion, and constructs responses by similarity-guided candidate selection. The system may be viewed as a rule extractor operating over a token graph rather than a conventional classifier. I formalize the knowledge base, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2208.00335","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-31T01:52:40Z","cross_cats_sorted":[],"title_canon_sha256":"9d4097d0fcf0a49b653679b6569176bd73152adbc2c668370ec3dd652ac06321","abstract_canon_sha256":"4e2f3a0731b6177bc94c95004407b21bcfcc005a0405d0413bb120cdea522ca1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:27.770033Z","signature_b64":"lrh1TV3sXTrS70v6yRl9H8uT1WfyOUbRfuVtIRmxzbRBaY8fYR1fziX+IfTVV9ifmrGzdl23BmuEQnykitZrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16d65fb6eb66f93d54f177cb7bc6d2a8d550f4fc4d0804171fb2849cdb9cc003","last_reissued_at":"2026-06-02T01:03:27.769592Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:27.769592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rule Extraction in Machine Learning: Chat Incremental Pattern Constructor","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"ChatIPC extracts ordered token-transition rules from text and builds responses by similarity selection on a token graph.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caleb Princewill Nwokocha","submitted_at":"2022-07-31T01:52:40Z","abstract_excerpt":"Rule extraction is a central problem in interpretable machine learning because it seeks to convert opaque predictive behavior into human-readable symbolic structure. This paper presents Chat Incremental Pattern Constructor (ChatIPC), a lightweight incremental symbolic learning system that extracts ordered token-transition rules from text, enriches them with definition-based expansion, and constructs responses by similarity-guided candidate selection. The system may be viewed as a rule extractor operating over a token graph rather than a conventional classifier. I formalize the knowledge base, "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ChatIPC is a lightweight incremental symbolic learning system that extracts ordered token-transition rules from text, enriches them with definition-based expansion, and constructs responses by similarity-guided candidate selection, operating over a token graph rather than a conventional classifier.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That similarity-guided selection on the token-transition graph, combined with definition expansion, will reliably produce coherent and useful responses (assumed without stated validation or comparison to baselines).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ChatIPC extracts ordered token-transition rules from text via incremental learning and definition expansion, then constructs responses through similarity-guided selection on a token graph.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ChatIPC extracts ordered token-transition rules from text and builds responses by similarity selection on a token graph.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8255a6ee4290c03d3bcde0b5ae1e7e04dfea70146bcd39dcd4624b229efe9a82"},"source":{"id":"2208.00335","kind":"arxiv","version":5},"verdict":{"id":"694b419c-de0c-43ec-9db6-efded1f77a6a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-24T11:17:48.771747Z","strongest_claim":"ChatIPC is a lightweight incremental symbolic learning system that extracts ordered token-transition rules from text, enriches them with definition-based expansion, and constructs responses by similarity-guided candidate selection, operating over a token graph rather than a conventional classifier.","one_line_summary":"ChatIPC extracts ordered token-transition rules from text via incremental learning and definition expansion, then constructs responses through similarity-guided selection on a token graph.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That similarity-guided selection on the token-transition graph, combined with definition expansion, will reliably produce coherent and useful responses (assumed without stated validation or comparison to baselines).","pith_extraction_headline":"ChatIPC extracts ordered token-transition rules from text and builds responses by similarity selection on a token graph."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2208.00335/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2208.00335","created_at":"2026-06-02T01:03:27.769647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.00335v5","created_at":"2026-06-02T01:03:27.769647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00335","created_at":"2026-06-02T01:03:27.769647+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3LF7NXLM34T","created_at":"2026-06-02T01:03:27.769647+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3LF7NXLM34T2VHR","created_at":"2026-06-02T01:03:27.769647+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3LF7NXL","created_at":"2026-06-02T01:03:27.769647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD","json":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD.json","graph_json":"https://pith.science/api/pith-number/C3LF7NXLM34T2VHRO7FXXRWSVD/graph.json","events_json":"https://pith.science/api/pith-number/C3LF7NXLM34T2VHRO7FXXRWSVD/events.json","paper":"https://pith.science/paper/C3LF7NXL"},"agent_actions":{"view_html":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD","download_json":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD.json","view_paper":"https://pith.science/paper/C3LF7NXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.00335&json=true","fetch_graph":"https://pith.science/api/pith-number/C3LF7NXLM34T2VHRO7FXXRWSVD/graph.json","fetch_events":"https://pith.science/api/pith-number/C3LF7NXLM34T2VHRO7FXXRWSVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD/action/storage_attestation","attest_author":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD/action/author_attestation","sign_citation":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD/action/citation_signature","submit_replication":"https://pith.science/pith/C3LF7NXLM34T2VHRO7FXXRWSVD/action/replication_record"}},"created_at":"2026-06-02T01:03:27.769647+00:00","updated_at":"2026-06-02T01:03:27.769647+00:00"}