{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:D7CXFNBBSKXFOR6WXVLRMHOJHR","short_pith_number":"pith:D7CXFNBB","schema_version":"1.0","canonical_sha256":"1fc572b42192ae5747d6bd57161dc93c5e138bd980e5028fd0f6930d8eab39f8","source":{"kind":"arxiv","id":"1910.08435","version":1},"attestation_state":"computed","paper":{"title":"Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Fan, Antoine Bordes, Chloe Braud, Claire Gardent","submitted_at":"2019-10-18T14:23:03Z","abstract_excerpt":"Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extractively select portions of web text as input to Sequence-to-Sequence models using methods such as TF-IDF ranking. We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy. We show that by linearizing the graph into a structured input sequence, models can encode the graph representations within a standard Sequence-to-Sequence setting. For two generative tasks with very long text input,"},"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":"1910.08435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-18T14:23:03Z","cross_cats_sorted":[],"title_canon_sha256":"59df029cad0510d256256e2ebf469af7e90ad866f5c242a54cf1311641241e97","abstract_canon_sha256":"9a61b4c69e04e808187bc9c2813eb3afaeb0917eb606ff88545b21a268594a21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:09.007070Z","signature_b64":"OaYrJGZGlOQBrD/1N2/xXZhdsOkzL7f33fNQk+9jMan7O+rqaBXe5ypNIdjDb15W6yL6t+YwU3G5OEuy9txbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fc572b42192ae5747d6bd57161dc93c5e138bd980e5028fd0f6930d8eab39f8","last_reissued_at":"2026-07-05T00:13:09.006645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:09.006645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Fan, Antoine Bordes, Chloe Braud, Claire Gardent","submitted_at":"2019-10-18T14:23:03Z","abstract_excerpt":"Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extractively select portions of web text as input to Sequence-to-Sequence models using methods such as TF-IDF ranking. We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy. We show that by linearizing the graph into a structured input sequence, models can encode the graph representations within a standard Sequence-to-Sequence setting. For two generative tasks with very long text input,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08435","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/1910.08435/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":"1910.08435","created_at":"2026-07-05T00:13:09.006705+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.08435v1","created_at":"2026-07-05T00:13:09.006705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08435","created_at":"2026-07-05T00:13:09.006705+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7CXFNBBSKXF","created_at":"2026-07-05T00:13:09.006705+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7CXFNBBSKXFOR6W","created_at":"2026-07-05T00:13:09.006705+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7CXFNBB","created_at":"2026-07-05T00:13:09.006705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":86,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR","json":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR.json","graph_json":"https://pith.science/api/pith-number/D7CXFNBBSKXFOR6WXVLRMHOJHR/graph.json","events_json":"https://pith.science/api/pith-number/D7CXFNBBSKXFOR6WXVLRMHOJHR/events.json","paper":"https://pith.science/paper/D7CXFNBB"},"agent_actions":{"view_html":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR","download_json":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR.json","view_paper":"https://pith.science/paper/D7CXFNBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.08435&json=true","fetch_graph":"https://pith.science/api/pith-number/D7CXFNBBSKXFOR6WXVLRMHOJHR/graph.json","fetch_events":"https://pith.science/api/pith-number/D7CXFNBBSKXFOR6WXVLRMHOJHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR/action/storage_attestation","attest_author":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR/action/author_attestation","sign_citation":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR/action/citation_signature","submit_replication":"https://pith.science/pith/D7CXFNBBSKXFOR6WXVLRMHOJHR/action/replication_record"}},"created_at":"2026-07-05T00:13:09.006705+00:00","updated_at":"2026-07-05T00:13:09.006705+00:00"}