{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JMSHY6UCCXYQN4OMRDIPF5F47A","short_pith_number":"pith:JMSHY6UC","schema_version":"1.0","canonical_sha256":"4b247c7a8215f106f1cc88d0f2f4bcf83ffffbef00c724ec94f1c9bee5f52a73","source":{"kind":"arxiv","id":"2608.06305","version":1},"attestation_state":"computed","paper":{"title":"Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Ayush Vyas, Sagar Tamang, Tabarakul Hazarika","submitted_at":"2026-08-06T17:23:13Z","abstract_excerpt":"Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundar"},"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":"2608.06305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:23:13Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"cbb56330904cc1c244636fd8c9949464a14b5ff73e41a601abb07c752802b146","abstract_canon_sha256":"c75f012c9e7484d5df46c6d6a560deedb80d3a875619a6d03267a1fa97a32ecb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:41:19.969898Z","signature_b64":"kLZf9EAlI4Yxt81k30QNo42LaLeo/YFSAu0o6ArkshUPpGRpd0mwQAcnjxnA8CPABNiPL6wS6gFTkEMHd2FLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b247c7a8215f106f1cc88d0f2f4bcf83ffffbef00c724ec94f1c9bee5f52a73","last_reissued_at":"2026-08-07T01:41:19.968481Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:41:19.968481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Ayush Vyas, Sagar Tamang, Tabarakul Hazarika","submitted_at":"2026-08-06T17:23:13Z","abstract_excerpt":"Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06305","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/2608.06305/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":"2608.06305","created_at":"2026-08-07T01:41:19.970969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06305v1","created_at":"2026-08-07T01:41:19.970969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06305","created_at":"2026-08-07T01:41:19.970969+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMSHY6UCCXYQ","created_at":"2026-08-07T01:41:19.970969+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMSHY6UCCXYQN4OM","created_at":"2026-08-07T01:41:19.970969+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMSHY6UC","created_at":"2026-08-07T01:41:19.970969+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/JMSHY6UCCXYQN4OMRDIPF5F47A","json":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A.json","graph_json":"https://pith.science/api/pith-number/JMSHY6UCCXYQN4OMRDIPF5F47A/graph.json","events_json":"https://pith.science/api/pith-number/JMSHY6UCCXYQN4OMRDIPF5F47A/events.json","paper":"https://pith.science/paper/JMSHY6UC"},"agent_actions":{"view_html":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A","download_json":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A.json","view_paper":"https://pith.science/paper/JMSHY6UC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06305&json=true","fetch_graph":"https://pith.science/api/pith-number/JMSHY6UCCXYQN4OMRDIPF5F47A/graph.json","fetch_events":"https://pith.science/api/pith-number/JMSHY6UCCXYQN4OMRDIPF5F47A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/action/storage_attestation","attest_author":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/action/author_attestation","sign_citation":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/action/citation_signature","submit_replication":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/action/replication_record"}},"created_at":"2026-08-07T01:41:19.970969+00:00","updated_at":"2026-08-07T01:41:19.970969+00:00"}