{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B4IXIUJLLV4F3JHXIBDC7DNVHS","short_pith_number":"pith:B4IXIUJL","schema_version":"1.0","canonical_sha256":"0f1174512b5d785da4f740462f8db53cbbc7b9411f82f21c4b984c7c641881d7","source":{"kind":"arxiv","id":"2606.29090","version":1},"attestation_state":"computed","paper":{"title":"AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Ansh Kamthan","submitted_at":"2026-06-27T21:08:14Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This wastes computation on easy questions, starves hard ones, and gives no signal for when a generated answer can be trusted. With a growing share of question answering systems built on top of commercial language model APIs, a method that can decide how much to retrieve, and how far to trust its own answers, without retraining the underlying model, is of clear practical value"},"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":"2606.29090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T21:08:14Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"159d04be6c9de766a5420f85338ae05ef9458fc91f792f7059eaf38cbdce69b1","abstract_canon_sha256":"2937416e10d9e933e20743dc55fd97e284a4562db5611648e7f2583573ab9839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:52.485714Z","signature_b64":"YA+hhEa2z9HJ+bxgd1Sgfpmb+zs1uwuFPEdH7q5Q2fP6pcyafk8+L+uJFEvIthiwTqh40H53hCIhXixsh/FnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f1174512b5d785da4f740462f8db53cbbc7b9411f82f21c4b984c7c641881d7","last_reissued_at":"2026-06-30T01:17:52.485238Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:52.485238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Ansh Kamthan","submitted_at":"2026-06-27T21:08:14Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This wastes computation on easy questions, starves hard ones, and gives no signal for when a generated answer can be trusted. With a growing share of question answering systems built on top of commercial language model APIs, a method that can decide how much to retrieve, and how far to trust its own answers, without retraining the underlying model, is of clear practical value"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29090","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/2606.29090/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":"2606.29090","created_at":"2026-06-30T01:17:52.485325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29090v1","created_at":"2026-06-30T01:17:52.485325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29090","created_at":"2026-06-30T01:17:52.485325+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4IXIUJLLV4F","created_at":"2026-06-30T01:17:52.485325+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4IXIUJLLV4F3JHX","created_at":"2026-06-30T01:17:52.485325+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4IXIUJL","created_at":"2026-06-30T01:17:52.485325+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/B4IXIUJLLV4F3JHXIBDC7DNVHS","json":"https://pith.science/pith/B4IXIUJLLV4F3JHXIBDC7DNVHS.json","graph_json":"https://pith.science/api/pith-number/B4IXIUJLLV4F3JHXIBDC7DNVHS/graph.json","events_json":"https://pith.science/api/pith-number/B4IXIUJLLV4F3JHXIBDC7DNVHS/events.json","paper":"https://pith.science/paper/B4IXIUJL"},"agent_actions":{"view_html":"https://pith.science/pith/B4IXIUJLLV4F3JHXIBDC7DNVHS","download_json":"https://pith.science/pith/B4IXIUJLLV4F3JHXIBDC7DNVHS.json","view_paper":"https://pith.science/paper/B4IXIUJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29090&json=true","fetch_graph":"https://pith.science/api/pith-number/B4IXIUJLLV4F3JHXIBDC7DNVHS/graph.json","fetch_events":"https://pith.science/api/pith-number/B4IXIUJLLV4F3JHXIBDC7DNVHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4IXIUJLLV4F3JHXIBDC7DNVHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4IXIUJLLV4F3JHXIBDC7DNVHS/action/storage_attestation","attest_author":"https://pith.science/pith/B4IXIUJLLV4F3JHXIBDC7DNVHS/action/author_attestation","sign_citation":"https://pith.science/pith/B4IXIUJLLV4F3JHXIBDC7DNVHS/action/citation_signature","submit_replication":"https://pith.science/pith/B4IXIUJLLV4F3JHXIBDC7DNVHS/action/replication_record"}},"created_at":"2026-06-30T01:17:52.485325+00:00","updated_at":"2026-06-30T01:17:52.485325+00:00"}