{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DMYFOC3LCICAYHHX6V3XKCYNDR","short_pith_number":"pith:DMYFOC3L","schema_version":"1.0","canonical_sha256":"1b30570b6b12040c1cf7f577750b0d1c458a181619ee51389b9145a60709bc7c","source":{"kind":"arxiv","id":"2107.07566","version":1},"attestation_state":"computed","paper":{"title":"Internet-Augmented Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jason Weston, Kurt Shuster, Mojtaba Komeili","submitted_at":"2021-07-15T19:00:35Z","abstract_excerpt":"The largest store of continually updating knowledge on our planet can be accessed via internet search. In this work we study giving access to this information to conversational agents. Large language models, even though they store an impressive amount of knowledge within their weights, are known to hallucinate facts when generating dialogue (Shuster et al., 2021); moreover, those facts are frozen in time at the point of model training. In contrast, we propose an approach that learns to generate an internet search query based on the context, and then conditions on the search results to finally "},"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":"2107.07566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-07-15T19:00:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"649474dd063e87c354ebf69155319f9b776070cf56c058df125b6cdf0230f6ab","abstract_canon_sha256":"9c940c75a341a409c8c15adaacf2104323ffa0736033322e12d13b3388741ba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:27.478448Z","signature_b64":"jQeq5GTBFyXDOnUAhmmW9nH3/PWYxOwJvN0J+v7H5zOoHw6s9BZawVESytT7Q1KKNz8us/OR+rT4PW+BLf8hBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b30570b6b12040c1cf7f577750b0d1c458a181619ee51389b9145a60709bc7c","last_reissued_at":"2026-07-05T02:58:27.478009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:27.478009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Internet-Augmented Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jason Weston, Kurt Shuster, Mojtaba Komeili","submitted_at":"2021-07-15T19:00:35Z","abstract_excerpt":"The largest store of continually updating knowledge on our planet can be accessed via internet search. In this work we study giving access to this information to conversational agents. Large language models, even though they store an impressive amount of knowledge within their weights, are known to hallucinate facts when generating dialogue (Shuster et al., 2021); moreover, those facts are frozen in time at the point of model training. In contrast, we propose an approach that learns to generate an internet search query based on the context, and then conditions on the search results to finally "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07566","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/2107.07566/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":"2107.07566","created_at":"2026-07-05T02:58:27.478064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.07566v1","created_at":"2026-07-05T02:58:27.478064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07566","created_at":"2026-07-05T02:58:27.478064+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMYFOC3LCICA","created_at":"2026-07-05T02:58:27.478064+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMYFOC3LCICAYHHX","created_at":"2026-07-05T02:58:27.478064+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMYFOC3L","created_at":"2026-07-05T02:58:27.478064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.11926","citing_title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19852","citing_title":"Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":213,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00739","citing_title":"Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2112.04426","citing_title":"Improving language models by retrieving from trillions of tokens","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2201.08239","citing_title":"LaMDA: Language Models for Dialog Applications","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2305.15334","citing_title":"Gorilla: Large Language Model Connected with Massive APIs","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22325","citing_title":"Dynamically Acquiring Text Content to Enable the Classification of Lesser-known Entities for Real-world Tasks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":257,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR","json":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR.json","graph_json":"https://pith.science/api/pith-number/DMYFOC3LCICAYHHX6V3XKCYNDR/graph.json","events_json":"https://pith.science/api/pith-number/DMYFOC3LCICAYHHX6V3XKCYNDR/events.json","paper":"https://pith.science/paper/DMYFOC3L"},"agent_actions":{"view_html":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR","download_json":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR.json","view_paper":"https://pith.science/paper/DMYFOC3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.07566&json=true","fetch_graph":"https://pith.science/api/pith-number/DMYFOC3LCICAYHHX6V3XKCYNDR/graph.json","fetch_events":"https://pith.science/api/pith-number/DMYFOC3LCICAYHHX6V3XKCYNDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR/action/storage_attestation","attest_author":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR/action/author_attestation","sign_citation":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR/action/citation_signature","submit_replication":"https://pith.science/pith/DMYFOC3LCICAYHHX6V3XKCYNDR/action/replication_record"}},"created_at":"2026-07-05T02:58:27.478064+00:00","updated_at":"2026-07-05T02:58:27.478064+00:00"}