{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CS6A3NPRH3LSAXXILOBYOKEHO3","short_pith_number":"pith:CS6A3NPR","schema_version":"1.0","canonical_sha256":"14bc0db5f13ed7205ee85b8387288776ff2a7ec597818891982a4a79b3fd47a3","source":{"kind":"arxiv","id":"2509.03527","version":1},"attestation_state":"computed","paper":{"title":"Multilevel Analysis of Cryptocurrency News using RAG Approach with Fine-Tuned Mistral Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bohdan M. Pavlyshenko","submitted_at":"2025-08-25T08:17:08Z","abstract_excerpt":"In the paper, we consider multilevel multitask analysis of cryptocurrency news using a fine-tuned Mistral 7B large language model with retrieval-augmented generation (RAG).\n  On the first level of analytics, the fine-tuned model generates graph and text summaries with sentiment scores as well as JSON representations of summaries. Higher levels perform hierarchical stacking that consolidates sets of graph-based and text-based summaries as well as summaries of summaries into comprehensive reports. The combination of graph and text summaries provides complementary views of cryptocurrency news. Th"},"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":"2509.03527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T08:17:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5fcd0fa2d78738a99e8b3b36f750299b88eb61a7945215af5f4d825134ecdebd","abstract_canon_sha256":"9694fae83eeedc41ba1c0b12c3e0c0e6dda7d7c3ea614950bd96bffa9061cd20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:41.600392Z","signature_b64":"38zbbfZsdvt6DCizxenimGFPCCEhS0CGC9M80VziORK3FnSpw3MtxnMq7ThcELTlIg7P5u3kprNva1IAU14/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14bc0db5f13ed7205ee85b8387288776ff2a7ec597818891982a4a79b3fd47a3","last_reissued_at":"2026-07-05T12:04:41.599754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:41.599754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilevel Analysis of Cryptocurrency News using RAG Approach with Fine-Tuned Mistral Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bohdan M. Pavlyshenko","submitted_at":"2025-08-25T08:17:08Z","abstract_excerpt":"In the paper, we consider multilevel multitask analysis of cryptocurrency news using a fine-tuned Mistral 7B large language model with retrieval-augmented generation (RAG).\n  On the first level of analytics, the fine-tuned model generates graph and text summaries with sentiment scores as well as JSON representations of summaries. Higher levels perform hierarchical stacking that consolidates sets of graph-based and text-based summaries as well as summaries of summaries into comprehensive reports. The combination of graph and text summaries provides complementary views of cryptocurrency news. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03527","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/2509.03527/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":"2509.03527","created_at":"2026-07-05T12:04:41.599831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03527v1","created_at":"2026-07-05T12:04:41.599831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03527","created_at":"2026-07-05T12:04:41.599831+00:00"},{"alias_kind":"pith_short_12","alias_value":"CS6A3NPRH3LS","created_at":"2026-07-05T12:04:41.599831+00:00"},{"alias_kind":"pith_short_16","alias_value":"CS6A3NPRH3LSAXXI","created_at":"2026-07-05T12:04:41.599831+00:00"},{"alias_kind":"pith_short_8","alias_value":"CS6A3NPR","created_at":"2026-07-05T12:04:41.599831+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/CS6A3NPRH3LSAXXILOBYOKEHO3","json":"https://pith.science/pith/CS6A3NPRH3LSAXXILOBYOKEHO3.json","graph_json":"https://pith.science/api/pith-number/CS6A3NPRH3LSAXXILOBYOKEHO3/graph.json","events_json":"https://pith.science/api/pith-number/CS6A3NPRH3LSAXXILOBYOKEHO3/events.json","paper":"https://pith.science/paper/CS6A3NPR"},"agent_actions":{"view_html":"https://pith.science/pith/CS6A3NPRH3LSAXXILOBYOKEHO3","download_json":"https://pith.science/pith/CS6A3NPRH3LSAXXILOBYOKEHO3.json","view_paper":"https://pith.science/paper/CS6A3NPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03527&json=true","fetch_graph":"https://pith.science/api/pith-number/CS6A3NPRH3LSAXXILOBYOKEHO3/graph.json","fetch_events":"https://pith.science/api/pith-number/CS6A3NPRH3LSAXXILOBYOKEHO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CS6A3NPRH3LSAXXILOBYOKEHO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CS6A3NPRH3LSAXXILOBYOKEHO3/action/storage_attestation","attest_author":"https://pith.science/pith/CS6A3NPRH3LSAXXILOBYOKEHO3/action/author_attestation","sign_citation":"https://pith.science/pith/CS6A3NPRH3LSAXXILOBYOKEHO3/action/citation_signature","submit_replication":"https://pith.science/pith/CS6A3NPRH3LSAXXILOBYOKEHO3/action/replication_record"}},"created_at":"2026-07-05T12:04:41.599831+00:00","updated_at":"2026-07-05T12:04:41.599831+00:00"}