{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJ3JT2CILR6T7XCIGRGPY2UEVX","short_pith_number":"pith:BJ3JT2CI","schema_version":"1.0","canonical_sha256":"0a7699e8485c7d3fdc48344cfc6a84adc8e9a39524c9d27ee046a64097363ca0","source":{"kind":"arxiv","id":"2406.13121","version":1},"attestation_state":"computed","paper":{"title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Aida Amini, Anthony Chen, Devendra Singh Sachan, Dheeru Dua, Hexiang Hu, Iftekhar Naim, Jeremy R. Cole, Jinhyuk Lee, Kelvin Guu, Michael Boratko, Ming-Wei Chang, Panupong Pasupat, Sebastian Riedel, S\\'ebastien M. R. Arnold, Siddharth Dalmia, Vincent Perot, Xudong Lin, Yi Luan, Zhuyun Dai","submitted_at":"2024-06-19T00:28:58Z","abstract_excerpt":"Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. Leveraging LCLMs' ability to natively ingest and process entire corpora of information offers numerous advantages. It enhances user-friendliness by eliminating the need for specialized knowledge of tools, provides robust end-to-end modeling that minimizes cascading errors in complex pipelines, and allows for the application of sophisticated prompting techniques across the entire system. To assess this paradigm shift, we intr"},"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":"2406.13121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T00:28:58Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"b1dc18fd09f49574473222e1d47349730ccab02fcbb85ceae3e07ed6353f2e23","abstract_canon_sha256":"842ede88ee125a3dcc4ea17e3fb6c6da161df351242d7013ffca110cc8517534"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:25.474025Z","signature_b64":"VC0IM8Syt1Cwn3vePyRdf92AWOA/VczANBIW25oBTjmEMv16swr3bmSjOzJEcKvVITpwWmvUeTkBxoZ0L8ENDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a7699e8485c7d3fdc48344cfc6a84adc8e9a39524c9d27ee046a64097363ca0","last_reissued_at":"2026-07-05T08:34:25.473614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:25.473614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Aida Amini, Anthony Chen, Devendra Singh Sachan, Dheeru Dua, Hexiang Hu, Iftekhar Naim, Jeremy R. Cole, Jinhyuk Lee, Kelvin Guu, Michael Boratko, Ming-Wei Chang, Panupong Pasupat, Sebastian Riedel, S\\'ebastien M. R. Arnold, Siddharth Dalmia, Vincent Perot, Xudong Lin, Yi Luan, Zhuyun Dai","submitted_at":"2024-06-19T00:28:58Z","abstract_excerpt":"Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. Leveraging LCLMs' ability to natively ingest and process entire corpora of information offers numerous advantages. It enhances user-friendliness by eliminating the need for specialized knowledge of tools, provides robust end-to-end modeling that minimizes cascading errors in complex pipelines, and allows for the application of sophisticated prompting techniques across the entire system. To assess this paradigm shift, we intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13121","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/2406.13121/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":"2406.13121","created_at":"2026-07-05T08:34:25.473673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13121v1","created_at":"2026-07-05T08:34:25.473673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13121","created_at":"2026-07-05T08:34:25.473673+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJ3JT2CILR6T","created_at":"2026-07-05T08:34:25.473673+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJ3JT2CILR6T7XCI","created_at":"2026-07-05T08:34:25.473673+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJ3JT2CI","created_at":"2026-07-05T08:34:25.473673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01538","citing_title":"Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13643","citing_title":"Recursive Agent Harnesses","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00288","citing_title":"Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24168","citing_title":"Inference Time Context Sparsity: Illusion or Opportunity?","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28079","citing_title":"ATLAS: All-round Testing of Long-context Abilities across Scales","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2507.06261","citing_title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03174","citing_title":"LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2402.08268","citing_title":"World Model on Million-Length Video And Language With Blockwise RingAttention","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2404.06654","citing_title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14810","citing_title":"Scalable Model-Based Clustering with Sequential Monte Carlo","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX","json":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX.json","graph_json":"https://pith.science/api/pith-number/BJ3JT2CILR6T7XCIGRGPY2UEVX/graph.json","events_json":"https://pith.science/api/pith-number/BJ3JT2CILR6T7XCIGRGPY2UEVX/events.json","paper":"https://pith.science/paper/BJ3JT2CI"},"agent_actions":{"view_html":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX","download_json":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX.json","view_paper":"https://pith.science/paper/BJ3JT2CI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13121&json=true","fetch_graph":"https://pith.science/api/pith-number/BJ3JT2CILR6T7XCIGRGPY2UEVX/graph.json","fetch_events":"https://pith.science/api/pith-number/BJ3JT2CILR6T7XCIGRGPY2UEVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX/action/storage_attestation","attest_author":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX/action/author_attestation","sign_citation":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX/action/citation_signature","submit_replication":"https://pith.science/pith/BJ3JT2CILR6T7XCIGRGPY2UEVX/action/replication_record"}},"created_at":"2026-07-05T08:34:25.473673+00:00","updated_at":"2026-07-05T08:34:25.473673+00:00"}