{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JWAOWOREEKTBKYJ22IGHDZJ36T","short_pith_number":"pith:JWAOWORE","schema_version":"1.0","canonical_sha256":"4d80eb3a2422a615613ad20c71e53bf4c3fc2d0580566309a085d6e459892b75","source":{"kind":"arxiv","id":"2606.07522","version":1},"attestation_state":"computed","paper":{"title":"Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.CL","authors_text":"Amitrajit Bhattacharjee, Julia Kruk, Mansi Phute, Sanchita Porwal","submitted_at":"2026-04-19T17:30:39Z","abstract_excerpt":"We propose an unsupervised method of resolving slang, unique entities, and folklore from online communities by isolating words in the lexicon that have the highest magnitude of semantic shift. Semantic shift is defined as the evolution of a word's encoded representation as a result of fine-tuning a pretrained Large Language Model (LLM) on a community-specific text corpus. This value is inversely proportional to the cosine similarity between the base model's encoded representation of a word, and a fine-tuned model's encoded representation. We fine-tune the DistilRoBERTa model on text corpora co"},"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":"2606.07522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T17:30:39Z","cross_cats_sorted":["cs.LG","cs.SI"],"title_canon_sha256":"6a4c33a0138be70e4ae8114ddd6e899c7b799516273d38d295ca3aa53063b3ca","abstract_canon_sha256":"9307a3c4834b115bd26532b1de47d48015984833363dad247168be493e44c2c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:41.369925Z","signature_b64":"0hzYoZxMDrTIx4AnbeiMFaNZFDo1RoJDH1V8cmp+IwX6WhU9P9QJcFHKZIVfVAEXD2Nd3eiTSz+XcPMdybBfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d80eb3a2422a615613ad20c71e53bf4c3fc2d0580566309a085d6e459892b75","last_reissued_at":"2026-06-09T00:04:41.369175Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:41.369175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.CL","authors_text":"Amitrajit Bhattacharjee, Julia Kruk, Mansi Phute, Sanchita Porwal","submitted_at":"2026-04-19T17:30:39Z","abstract_excerpt":"We propose an unsupervised method of resolving slang, unique entities, and folklore from online communities by isolating words in the lexicon that have the highest magnitude of semantic shift. Semantic shift is defined as the evolution of a word's encoded representation as a result of fine-tuning a pretrained Large Language Model (LLM) on a community-specific text corpus. This value is inversely proportional to the cosine similarity between the base model's encoded representation of a word, and a fine-tuned model's encoded representation. We fine-tune the DistilRoBERTa model on text corpora co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07522","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.07522/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":"2606.07522","created_at":"2026-06-09T00:04:41.369268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07522v1","created_at":"2026-06-09T00:04:41.369268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07522","created_at":"2026-06-09T00:04:41.369268+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWAOWOREEKTB","created_at":"2026-06-09T00:04:41.369268+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWAOWOREEKTBKYJ2","created_at":"2026-06-09T00:04:41.369268+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWAOWORE","created_at":"2026-06-09T00:04:41.369268+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/JWAOWOREEKTBKYJ22IGHDZJ36T","json":"https://pith.science/pith/JWAOWOREEKTBKYJ22IGHDZJ36T.json","graph_json":"https://pith.science/api/pith-number/JWAOWOREEKTBKYJ22IGHDZJ36T/graph.json","events_json":"https://pith.science/api/pith-number/JWAOWOREEKTBKYJ22IGHDZJ36T/events.json","paper":"https://pith.science/paper/JWAOWORE"},"agent_actions":{"view_html":"https://pith.science/pith/JWAOWOREEKTBKYJ22IGHDZJ36T","download_json":"https://pith.science/pith/JWAOWOREEKTBKYJ22IGHDZJ36T.json","view_paper":"https://pith.science/paper/JWAOWORE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07522&json=true","fetch_graph":"https://pith.science/api/pith-number/JWAOWOREEKTBKYJ22IGHDZJ36T/graph.json","fetch_events":"https://pith.science/api/pith-number/JWAOWOREEKTBKYJ22IGHDZJ36T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWAOWOREEKTBKYJ22IGHDZJ36T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWAOWOREEKTBKYJ22IGHDZJ36T/action/storage_attestation","attest_author":"https://pith.science/pith/JWAOWOREEKTBKYJ22IGHDZJ36T/action/author_attestation","sign_citation":"https://pith.science/pith/JWAOWOREEKTBKYJ22IGHDZJ36T/action/citation_signature","submit_replication":"https://pith.science/pith/JWAOWOREEKTBKYJ22IGHDZJ36T/action/replication_record"}},"created_at":"2026-06-09T00:04:41.369268+00:00","updated_at":"2026-06-09T00:04:41.369268+00:00"}