{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GQNJSKUQGRZZFLEUSRON75PWKR","short_pith_number":"pith:GQNJSKUQ","canonical_record":{"source":{"id":"2501.13880","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T17:54:19Z","cross_cats_sorted":[],"title_canon_sha256":"7e19245251477b714b2968758b1075d96c9bead9377d90934940f96449b3628f","abstract_canon_sha256":"d8e347f555990705756798c87b384a2820f5ec574a8a0b7d0ee7986ad3e15519"},"schema_version":"1.0"},"canonical_sha256":"341a992a90347392ac94945cdff5f65456a90d2e304a980385552a2a8cca69c8","source":{"kind":"arxiv","id":"2501.13880","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13880","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13880v1","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13880","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"GQNJSKUQGRZZ","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"GQNJSKUQGRZZFLEU","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"GQNJSKUQ","created_at":"2026-07-05T10:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GQNJSKUQGRZZFLEUSRON75PWKR","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13880","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T17:54:19Z","cross_cats_sorted":[],"title_canon_sha256":"7e19245251477b714b2968758b1075d96c9bead9377d90934940f96449b3628f","abstract_canon_sha256":"d8e347f555990705756798c87b384a2820f5ec574a8a0b7d0ee7986ad3e15519"},"schema_version":"1.0"},"canonical_sha256":"341a992a90347392ac94945cdff5f65456a90d2e304a980385552a2a8cca69c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:35.613620Z","signature_b64":"ShOBNzP0hGVwEZ7Y9+3k6cKtstkQnySO1DXp95N7kyrqIRYTtS2NNXiTZjBAfE2DIp57xyrBNk58u6YCYfRPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"341a992a90347392ac94945cdff5f65456a90d2e304a980385552a2a8cca69c8","last_reissued_at":"2026-07-05T10:04:35.613266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:35.613266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13880","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l8iObeXcyQHFWMeEpF1LpFvxph7UACtwe0vuPU5Gzgmo9q0ooejjgweaRATjAodzs0kIEp80xDtH4LJcmNxwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:05:33.437284Z"},"content_sha256":"e64fc7c2bb8022cea7455c5604c59032579efc9fc3f60fdeef92c4b9b7efc19d","schema_version":"1.0","event_id":"sha256:e64fc7c2bb8022cea7455c5604c59032579efc9fc3f60fdeef92c4b9b7efc19d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GQNJSKUQGRZZFLEUSRON75PWKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A RAG-Based Institutional Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fabio G. Cozman, Gustavo Kuratomi, Paulo Pirozelli, Sarajane M. Peres","submitted_at":"2025-01-23T17:54:19Z","abstract_excerpt":"Although large language models (LLMs) demonstrate strong text generation capabilities, they struggle in scenarios requiring access to structured knowledge bases or specific documents, limiting their effectiveness in knowledge-intensive tasks. To address this limitation, retrieval-augmented generation (RAG) models have been developed, enabling generative models to incorporate relevant document fragments into their inputs. In this paper, we design and evaluate a RAG-based virtual assistant specifically tailored for the University of S\\~ao Paulo. Our system architecture comprises two key modules:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13880","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/2501.13880/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":"2026-07-05T10:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6hlACJKn7kMlJC//KngWBF8CxPc/25mOn7KIbfwvnmlQofIau1wITEIT2dtAvEEBWHOXDeuPjYpYtQB8dNKzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:05:33.437784Z"},"content_sha256":"be04c1a11bc90632f69944759e10e655fcdf6d2e80911e9127f79d2408a4b3c0","schema_version":"1.0","event_id":"sha256:be04c1a11bc90632f69944759e10e655fcdf6d2e80911e9127f79d2408a4b3c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/bundle.json","state_url":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQNJSKUQGRZZFLEUSRON75PWKR/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":"2026-08-06T03:05:33Z","links":{"resolver":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR","bundle":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/bundle.json","state":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQNJSKUQGRZZFLEUSRON75PWKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GQNJSKUQGRZZFLEUSRON75PWKR","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":"d8e347f555990705756798c87b384a2820f5ec574a8a0b7d0ee7986ad3e15519","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T17:54:19Z","title_canon_sha256":"7e19245251477b714b2968758b1075d96c9bead9377d90934940f96449b3628f"},"schema_version":"1.0","source":{"id":"2501.13880","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13880","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13880v1","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13880","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"GQNJSKUQGRZZ","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"GQNJSKUQGRZZFLEU","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"GQNJSKUQ","created_at":"2026-07-05T10:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:be04c1a11bc90632f69944759e10e655fcdf6d2e80911e9127f79d2408a4b3c0","target":"graph","created_at":"2026-07-05T10:04:35Z","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/2501.13880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large language models (LLMs) demonstrate strong text generation capabilities, they struggle in scenarios requiring access to structured knowledge bases or specific documents, limiting their effectiveness in knowledge-intensive tasks. To address this limitation, retrieval-augmented generation (RAG) models have been developed, enabling generative models to incorporate relevant document fragments into their inputs. In this paper, we design and evaluate a RAG-based virtual assistant specifically tailored for the University of S\\~ao Paulo. Our system architecture comprises two key modules:","authors_text":"Fabio G. Cozman, Gustavo Kuratomi, Paulo Pirozelli, Sarajane M. Peres","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T17:54:19Z","title":"A RAG-Based Institutional Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13880","kind":"arxiv","version":1},"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:e64fc7c2bb8022cea7455c5604c59032579efc9fc3f60fdeef92c4b9b7efc19d","target":"record","created_at":"2026-07-05T10:04:35Z","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":"d8e347f555990705756798c87b384a2820f5ec574a8a0b7d0ee7986ad3e15519","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T17:54:19Z","title_canon_sha256":"7e19245251477b714b2968758b1075d96c9bead9377d90934940f96449b3628f"},"schema_version":"1.0","source":{"id":"2501.13880","kind":"arxiv","version":1}},"canonical_sha256":"341a992a90347392ac94945cdff5f65456a90d2e304a980385552a2a8cca69c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"341a992a90347392ac94945cdff5f65456a90d2e304a980385552a2a8cca69c8","first_computed_at":"2026-07-05T10:04:35.613266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:35.613266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ShOBNzP0hGVwEZ7Y9+3k6cKtstkQnySO1DXp95N7kyrqIRYTtS2NNXiTZjBAfE2DIp57xyrBNk58u6YCYfRPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:35.613620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13880","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e64fc7c2bb8022cea7455c5604c59032579efc9fc3f60fdeef92c4b9b7efc19d","sha256:be04c1a11bc90632f69944759e10e655fcdf6d2e80911e9127f79d2408a4b3c0"],"state_sha256":"6a6e60cc943e0c9409202f716032ceb4529a29accf53e17dfc3e5860f4f00b36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BUBvyF6H6e6GZkvqNC22QN+q2HfM6S6Ra6Y7I1Xij8C72O04XM9NzwPKihkTa+MM7knI5fQn3TeTXbK12qxBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:05:33.442738Z","bundle_sha256":"fe132f69e4725e0f7dab5ec2de20fc9c30568c46bff359d929d4a2bbff161282"}}