{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GJTTDEFDSPN2VMROVUJBWRX4C4","short_pith_number":"pith:GJTTDEFD","schema_version":"1.0","canonical_sha256":"32673190a393dbaab22ead121b46fc1700f8a5b927fbf22160cf1a243dabfcc3","source":{"kind":"arxiv","id":"2606.10716","version":1},"attestation_state":"computed","paper":{"title":"Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alvaro J. L\\'opez-L\\'opez, Jos\\'e Portela, Roberto Mart\\'inez-Cruz","submitted_at":"2026-06-09T11:24:07Z","abstract_excerpt":"Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich contextualized representations. However, long-document KPE remains challenging because salient keyphrase evidence may be scattered across distant document sections that cannot be jointly captured within the limited context window of most PLMs. Although long-context large language models (LLMs) can process broader textual contexts, their computational cost limits their practicality for efficient and high-throughput KPE. To overcome this limitation, we "},"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":"2606.10716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T11:24:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"420e353d74520ba8fa40985d4e1ae3a947044fe3e6dfa1d14d5eec1ffd9d2f80","abstract_canon_sha256":"450e19116c94526b2d4642e9e3792010048fc5a71ea1756245bf3e1d52e79ac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:36.107121Z","signature_b64":"3xirlXRSoU1sBudz3+djtd3DP/qPAy92gEtjeeb8O/bHom++aJNDbD1RJ/sU8Kjg5i7c53GImXWemIvbt7u1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32673190a393dbaab22ead121b46fc1700f8a5b927fbf22160cf1a243dabfcc3","last_reissued_at":"2026-06-10T01:10:36.106186Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:36.106186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alvaro J. L\\'opez-L\\'opez, Jos\\'e Portela, Roberto Mart\\'inez-Cruz","submitted_at":"2026-06-09T11:24:07Z","abstract_excerpt":"Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich contextualized representations. However, long-document KPE remains challenging because salient keyphrase evidence may be scattered across distant document sections that cannot be jointly captured within the limited context window of most PLMs. Although long-context large language models (LLMs) can process broader textual contexts, their computational cost limits their practicality for efficient and high-throughput KPE. To overcome this limitation, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10716","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/2606.10716/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":"2606.10716","created_at":"2026-06-10T01:10:36.106312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10716v1","created_at":"2026-06-10T01:10:36.106312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10716","created_at":"2026-06-10T01:10:36.106312+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJTTDEFDSPN2","created_at":"2026-06-10T01:10:36.106312+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJTTDEFDSPN2VMRO","created_at":"2026-06-10T01:10:36.106312+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJTTDEFD","created_at":"2026-06-10T01:10:36.106312+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/GJTTDEFDSPN2VMROVUJBWRX4C4","json":"https://pith.science/pith/GJTTDEFDSPN2VMROVUJBWRX4C4.json","graph_json":"https://pith.science/api/pith-number/GJTTDEFDSPN2VMROVUJBWRX4C4/graph.json","events_json":"https://pith.science/api/pith-number/GJTTDEFDSPN2VMROVUJBWRX4C4/events.json","paper":"https://pith.science/paper/GJTTDEFD"},"agent_actions":{"view_html":"https://pith.science/pith/GJTTDEFDSPN2VMROVUJBWRX4C4","download_json":"https://pith.science/pith/GJTTDEFDSPN2VMROVUJBWRX4C4.json","view_paper":"https://pith.science/paper/GJTTDEFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10716&json=true","fetch_graph":"https://pith.science/api/pith-number/GJTTDEFDSPN2VMROVUJBWRX4C4/graph.json","fetch_events":"https://pith.science/api/pith-number/GJTTDEFDSPN2VMROVUJBWRX4C4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJTTDEFDSPN2VMROVUJBWRX4C4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJTTDEFDSPN2VMROVUJBWRX4C4/action/storage_attestation","attest_author":"https://pith.science/pith/GJTTDEFDSPN2VMROVUJBWRX4C4/action/author_attestation","sign_citation":"https://pith.science/pith/GJTTDEFDSPN2VMROVUJBWRX4C4/action/citation_signature","submit_replication":"https://pith.science/pith/GJTTDEFDSPN2VMROVUJBWRX4C4/action/replication_record"}},"created_at":"2026-06-10T01:10:36.106312+00:00","updated_at":"2026-06-10T01:10:36.106312+00:00"}