{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RQGNEUT6WEHJD5AW2CH3LAHQBL","short_pith_number":"pith:RQGNEUT6","canonical_record":{"source":{"id":"2402.05140","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T20:11:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1fd7d7a348d3c41c4d041d7f2e90c628be537ff4240e0bc0fd34575784453d8f","abstract_canon_sha256":"e4e6e885098a3f0160c19f854df14a4eb05d79266afb902cfa8ec49d0eb862e3"},"schema_version":"1.0"},"canonical_sha256":"8c0cd2527eb10e91f416d08fb580f00af8b73ca9a8a9f7b0796cf9de484f6762","source":{"kind":"arxiv","id":"2402.05140","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05140","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05140v3","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05140","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"RQGNEUT6WEHJ","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"RQGNEUT6WEHJD5AW","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"RQGNEUT6","created_at":"2026-07-05T08:48:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RQGNEUT6WEHJD5AW2CH3LAHQBL","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05140","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T20:11:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1fd7d7a348d3c41c4d041d7f2e90c628be537ff4240e0bc0fd34575784453d8f","abstract_canon_sha256":"e4e6e885098a3f0160c19f854df14a4eb05d79266afb902cfa8ec49d0eb862e3"},"schema_version":"1.0"},"canonical_sha256":"8c0cd2527eb10e91f416d08fb580f00af8b73ca9a8a9f7b0796cf9de484f6762","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:41.044417Z","signature_b64":"UegVCQpoj1VJ3OrLLsytApjymMgIbdH2S/vq/CgU8PBIPWjASyAi0aqKDIIGMXtgwhExBUwtutNGLMd2h6LHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c0cd2527eb10e91f416d08fb580f00af8b73ca9a8a9f7b0796cf9de484f6762","last_reissued_at":"2026-07-05T08:48:41.044003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:41.044003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05140","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q3knc51mDT4we09NJPkpX8sDaxja6zIx+zcxf1RrjjCeUOA1XXwgfx63CWjASJBETli0is5jvRSXo3aVcrOnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:36:28.907320Z"},"content_sha256":"c4f3728f9c43219c72fd2b79c96e1e9572aba54ed5491fd72b2e78e67dfe21c7","schema_version":"1.0","event_id":"sha256:c4f3728f9c43219c72fd2b79c96e1e9572aba54ed5491fd72b2e78e67dfe21c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RQGNEUT6WEHJD5AW2CH3LAHQBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, James Brian Hall, Junhong Shen, Neil Tenenholtz, Nicolo Fusi","submitted_at":"2024-02-06T20:11:54Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domains underrepresented in the pretraining corpus, such as physical and biomedical sciences. This work explores how to repurpose general LLMs into effective task solvers for specialized domains. We introduce a novel, model-agnostic framework for learning custom input tags, which are parameterized as continuous vectors appended to the LLM's embedding layer, to condition the LLM. We design two types of input tags: domain t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05140","kind":"arxiv","version":3},"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/2402.05140/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":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ewkdwqx2ZQVABkDnlhGyvMLndl76U957GIZpiZ+2Oywv5FiLAB8Wza+gKVFGTCR2ckI81/MRUUnUOJZGeiTpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:36:28.908032Z"},"content_sha256":"55ea90d6fc92d0a27907927641cb1d5bef8d76f28822bddc5bd73b0c487fd189","schema_version":"1.0","event_id":"sha256:55ea90d6fc92d0a27907927641cb1d5bef8d76f28822bddc5bd73b0c487fd189"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RQGNEUT6WEHJD5AW2CH3LAHQBL/bundle.json","state_url":"https://pith.science/pith/RQGNEUT6WEHJD5AW2CH3LAHQBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RQGNEUT6WEHJD5AW2CH3LAHQBL/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":"2026-08-08T23:36:28Z","links":{"resolver":"https://pith.science/pith/RQGNEUT6WEHJD5AW2CH3LAHQBL","bundle":"https://pith.science/pith/RQGNEUT6WEHJD5AW2CH3LAHQBL/bundle.json","state":"https://pith.science/pith/RQGNEUT6WEHJD5AW2CH3LAHQBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RQGNEUT6WEHJD5AW2CH3LAHQBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RQGNEUT6WEHJD5AW2CH3LAHQBL","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":"e4e6e885098a3f0160c19f854df14a4eb05d79266afb902cfa8ec49d0eb862e3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T20:11:54Z","title_canon_sha256":"1fd7d7a348d3c41c4d041d7f2e90c628be537ff4240e0bc0fd34575784453d8f"},"schema_version":"1.0","source":{"id":"2402.05140","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05140","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05140v3","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05140","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"RQGNEUT6WEHJ","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"RQGNEUT6WEHJD5AW","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"RQGNEUT6","created_at":"2026-07-05T08:48:41Z"}],"graph_snapshots":[{"event_id":"sha256:55ea90d6fc92d0a27907927641cb1d5bef8d76f28822bddc5bd73b0c487fd189","target":"graph","created_at":"2026-07-05T08:48:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.05140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domains underrepresented in the pretraining corpus, such as physical and biomedical sciences. This work explores how to repurpose general LLMs into effective task solvers for specialized domains. We introduce a novel, model-agnostic framework for learning custom input tags, which are parameterized as continuous vectors appended to the LLM's embedding layer, to condition the LLM. We design two types of input tags: domain t","authors_text":"David Alvarez-Melis, James Brian Hall, Junhong Shen, Neil Tenenholtz, Nicolo Fusi","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T20:11:54Z","title":"Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05140","kind":"arxiv","version":3},"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:c4f3728f9c43219c72fd2b79c96e1e9572aba54ed5491fd72b2e78e67dfe21c7","target":"record","created_at":"2026-07-05T08:48:41Z","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":"e4e6e885098a3f0160c19f854df14a4eb05d79266afb902cfa8ec49d0eb862e3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T20:11:54Z","title_canon_sha256":"1fd7d7a348d3c41c4d041d7f2e90c628be537ff4240e0bc0fd34575784453d8f"},"schema_version":"1.0","source":{"id":"2402.05140","kind":"arxiv","version":3}},"canonical_sha256":"8c0cd2527eb10e91f416d08fb580f00af8b73ca9a8a9f7b0796cf9de484f6762","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c0cd2527eb10e91f416d08fb580f00af8b73ca9a8a9f7b0796cf9de484f6762","first_computed_at":"2026-07-05T08:48:41.044003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:41.044003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UegVCQpoj1VJ3OrLLsytApjymMgIbdH2S/vq/CgU8PBIPWjASyAi0aqKDIIGMXtgwhExBUwtutNGLMd2h6LHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:41.044417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05140","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4f3728f9c43219c72fd2b79c96e1e9572aba54ed5491fd72b2e78e67dfe21c7","sha256:55ea90d6fc92d0a27907927641cb1d5bef8d76f28822bddc5bd73b0c487fd189"],"state_sha256":"a60740a1e61335b3b3adf81e7686540dbeb19d3cdfbaac0783d1010993a7f67f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jGUilotqbEpx/6/+NCHpHMoNedi1WXfasBu8MdbpO+xMGObbkRdyIEYntQJKAxo/wZ+xWelS9jjKxKnLlPgmDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:36:28.913335Z","bundle_sha256":"7d386ad5e3197882a40beb6be62af1226f0ff4bc6faadb826d02a5e7d3200cf3"}}