{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7LCUWCPGFU26JB3XR4LARZSRKA","short_pith_number":"pith:7LCUWCPG","schema_version":"1.0","canonical_sha256":"fac54b09e62d35e487778f1608e651501d442df8efe6f099194012221530375a","source":{"kind":"arxiv","id":"2506.19527","version":1},"attestation_state":"computed","paper":{"title":"KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaigui Bian, Kelin Fu","submitted_at":"2025-06-24T11:30:38Z","abstract_excerpt":"While Large Language Models (LLMs) possess significant capabilities in open-world agent tasks, they also face challenges in rapidly adapting to new, specialized tasks due to their reliance on static pre-trained knowledge. Traditional methods such as fine-tuning are often costly, data-intensive, and may lead to \"catastrophic forgetting.\" Therefore, we present KnowMap, a novel approach that dynamically constructs a knowledge base from environmental and experiential data. KnowMap fine-tunes a small knowledge-embedding model to equip a larger LLM with valuable task-specific knowledge. Our experime"},"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":"2506.19527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T11:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"b2b105720eda61614771870a97963d649b25ca92ff3d34e0a0a261b5d7b4d526","abstract_canon_sha256":"20c9b54d729e19f065b089f389bb6862c22e1f0209f2fed506f7e1ea76240136"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:34.080748Z","signature_b64":"abA+R3JM13yrlU7OQkOfsWF0thFUyqAY+3/aS4bikLMFBPdNoO8exdmiPixfhLAnqeNxvwCMCgmqlhISa2qVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fac54b09e62d35e487778f1608e651501d442df8efe6f099194012221530375a","last_reissued_at":"2026-07-05T11:26:34.080246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:34.080246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaigui Bian, Kelin Fu","submitted_at":"2025-06-24T11:30:38Z","abstract_excerpt":"While Large Language Models (LLMs) possess significant capabilities in open-world agent tasks, they also face challenges in rapidly adapting to new, specialized tasks due to their reliance on static pre-trained knowledge. Traditional methods such as fine-tuning are often costly, data-intensive, and may lead to \"catastrophic forgetting.\" Therefore, we present KnowMap, a novel approach that dynamically constructs a knowledge base from environmental and experiential data. KnowMap fine-tunes a small knowledge-embedding model to equip a larger LLM with valuable task-specific knowledge. Our experime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19527","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/2506.19527/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":"2506.19527","created_at":"2026-07-05T11:26:34.080302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19527v1","created_at":"2026-07-05T11:26:34.080302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19527","created_at":"2026-07-05T11:26:34.080302+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LCUWCPGFU26","created_at":"2026-07-05T11:26:34.080302+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LCUWCPGFU26JB3X","created_at":"2026-07-05T11:26:34.080302+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LCUWCPG","created_at":"2026-07-05T11:26:34.080302+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/7LCUWCPGFU26JB3XR4LARZSRKA","json":"https://pith.science/pith/7LCUWCPGFU26JB3XR4LARZSRKA.json","graph_json":"https://pith.science/api/pith-number/7LCUWCPGFU26JB3XR4LARZSRKA/graph.json","events_json":"https://pith.science/api/pith-number/7LCUWCPGFU26JB3XR4LARZSRKA/events.json","paper":"https://pith.science/paper/7LCUWCPG"},"agent_actions":{"view_html":"https://pith.science/pith/7LCUWCPGFU26JB3XR4LARZSRKA","download_json":"https://pith.science/pith/7LCUWCPGFU26JB3XR4LARZSRKA.json","view_paper":"https://pith.science/paper/7LCUWCPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19527&json=true","fetch_graph":"https://pith.science/api/pith-number/7LCUWCPGFU26JB3XR4LARZSRKA/graph.json","fetch_events":"https://pith.science/api/pith-number/7LCUWCPGFU26JB3XR4LARZSRKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LCUWCPGFU26JB3XR4LARZSRKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LCUWCPGFU26JB3XR4LARZSRKA/action/storage_attestation","attest_author":"https://pith.science/pith/7LCUWCPGFU26JB3XR4LARZSRKA/action/author_attestation","sign_citation":"https://pith.science/pith/7LCUWCPGFU26JB3XR4LARZSRKA/action/citation_signature","submit_replication":"https://pith.science/pith/7LCUWCPGFU26JB3XR4LARZSRKA/action/replication_record"}},"created_at":"2026-07-05T11:26:34.080302+00:00","updated_at":"2026-07-05T11:26:34.080302+00:00"}