{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KU2QVYSQ5AD2FVKK7VL6MZDSNV","short_pith_number":"pith:KU2QVYSQ","schema_version":"1.0","canonical_sha256":"55350ae250e807a2d54afd57e664726d541ecc42069b4c2bf03e8928b35144d9","source":{"kind":"arxiv","id":"2106.01703","version":1},"attestation_state":"computed","paper":{"title":"Fingerprinting Fine-tuned Language Models in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nirav Diwan, Tanmoy Chakravorty, Zubair Shafiq","submitted_at":"2021-06-03T09:07:54Z","abstract_excerpt":"There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, disinformation, or propaganda. Therefore, the research community is actively working on developing approaches to detect whether a given text is organic or synthetic. While this is a useful first step, it is important to be able to further fingerprint the author LM to attribute its origin. Prior work on fingerprinting LMs is limited to attributing synthetic text generated by a handful (usually < 10) of pre-trained LMs. However, LMs such as GPT2 are commonly fine-tu"},"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":"2106.01703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-03T09:07:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"892133454501d851aaf924c34947461eb66cbba6e2dac6f78c06a63a8ecd804d","abstract_canon_sha256":"f78a68baad45406e0aaa89f46abff331909d91da726359188abd846f5068f351"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:03.691976Z","signature_b64":"w2Bm4kiT01bxrJY7GV1pX0ARaE7nF84Qj46IuaBN+iPCFS6lDIx79fWRkbAE3D5l3ywz8qdedwoP6wIlZWcuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55350ae250e807a2d54afd57e664726d541ecc42069b4c2bf03e8928b35144d9","last_reissued_at":"2026-07-05T02:46:03.691547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:03.691547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fingerprinting Fine-tuned Language Models in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nirav Diwan, Tanmoy Chakravorty, Zubair Shafiq","submitted_at":"2021-06-03T09:07:54Z","abstract_excerpt":"There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, disinformation, or propaganda. Therefore, the research community is actively working on developing approaches to detect whether a given text is organic or synthetic. While this is a useful first step, it is important to be able to further fingerprint the author LM to attribute its origin. Prior work on fingerprinting LMs is limited to attributing synthetic text generated by a handful (usually < 10) of pre-trained LMs. However, LMs such as GPT2 are commonly fine-tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01703","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/2106.01703/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":"2106.01703","created_at":"2026-07-05T02:46:03.691605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01703v1","created_at":"2026-07-05T02:46:03.691605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01703","created_at":"2026-07-05T02:46:03.691605+00:00"},{"alias_kind":"pith_short_12","alias_value":"KU2QVYSQ5AD2","created_at":"2026-07-05T02:46:03.691605+00:00"},{"alias_kind":"pith_short_16","alias_value":"KU2QVYSQ5AD2FVKK","created_at":"2026-07-05T02:46:03.691605+00:00"},{"alias_kind":"pith_short_8","alias_value":"KU2QVYSQ","created_at":"2026-07-05T02:46:03.691605+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/KU2QVYSQ5AD2FVKK7VL6MZDSNV","json":"https://pith.science/pith/KU2QVYSQ5AD2FVKK7VL6MZDSNV.json","graph_json":"https://pith.science/api/pith-number/KU2QVYSQ5AD2FVKK7VL6MZDSNV/graph.json","events_json":"https://pith.science/api/pith-number/KU2QVYSQ5AD2FVKK7VL6MZDSNV/events.json","paper":"https://pith.science/paper/KU2QVYSQ"},"agent_actions":{"view_html":"https://pith.science/pith/KU2QVYSQ5AD2FVKK7VL6MZDSNV","download_json":"https://pith.science/pith/KU2QVYSQ5AD2FVKK7VL6MZDSNV.json","view_paper":"https://pith.science/paper/KU2QVYSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01703&json=true","fetch_graph":"https://pith.science/api/pith-number/KU2QVYSQ5AD2FVKK7VL6MZDSNV/graph.json","fetch_events":"https://pith.science/api/pith-number/KU2QVYSQ5AD2FVKK7VL6MZDSNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KU2QVYSQ5AD2FVKK7VL6MZDSNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KU2QVYSQ5AD2FVKK7VL6MZDSNV/action/storage_attestation","attest_author":"https://pith.science/pith/KU2QVYSQ5AD2FVKK7VL6MZDSNV/action/author_attestation","sign_citation":"https://pith.science/pith/KU2QVYSQ5AD2FVKK7VL6MZDSNV/action/citation_signature","submit_replication":"https://pith.science/pith/KU2QVYSQ5AD2FVKK7VL6MZDSNV/action/replication_record"}},"created_at":"2026-07-05T02:46:03.691605+00:00","updated_at":"2026-07-05T02:46:03.691605+00:00"}