{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N6JSGJ2NRVIMRR2BTMLQOSMHIG","short_pith_number":"pith:N6JSGJ2N","schema_version":"1.0","canonical_sha256":"6f9323274d8d50c8c7419b1707498741ba6755105ea5f0e56e08205017530975","source":{"kind":"arxiv","id":"2605.15562","version":1},"attestation_state":"computed","paper":{"title":"GiLT: Augmenting Transformer Language Models with Dependency Graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuyan Zhou, Kewei Tu, Tianyu Huang, Yida Zhao","submitted_at":"2026-05-15T03:08:49Z","abstract_excerpt":"Augmenting Transformers with linguistic structures effectively enhances the syntactic generalization performance of language models. Previous work in this direction focuses on syntactic tree structures of languages, in particular constituency tree structures. We propose Graph-Infused Layers Transformer Language Model (GiLT) which leverages dependency graphs for augmenting Transformer language models. Unlike most previous work, GiLT does not insert extra structural tokens in language modeling; instead, it injects structural information into language modeling by modulating attention weights in t"},"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":"2605.15562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T03:08:49Z","cross_cats_sorted":[],"title_canon_sha256":"c1a1ee7e6cb8a595f0f333a953df326a0f234a54b4350df0ef9e90c588646960","abstract_canon_sha256":"f8605781185ce26460d881c13b4d6f5f1d90be98d11248fbea3e115769f15eca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:05.477994Z","signature_b64":"z84ywlMd/4PhPS8aNXZB+bBGUf5rFXZHPpuoCxtqRNxBbpC/cKHtddHbjE1H2xGM+IObs7yYQ6UPqA+wZmT/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f9323274d8d50c8c7419b1707498741ba6755105ea5f0e56e08205017530975","last_reissued_at":"2026-05-20T00:01:05.477157Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:05.477157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GiLT: Augmenting Transformer Language Models with Dependency Graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuyan Zhou, Kewei Tu, Tianyu Huang, Yida Zhao","submitted_at":"2026-05-15T03:08:49Z","abstract_excerpt":"Augmenting Transformers with linguistic structures effectively enhances the syntactic generalization performance of language models. Previous work in this direction focuses on syntactic tree structures of languages, in particular constituency tree structures. We propose Graph-Infused Layers Transformer Language Model (GiLT) which leverages dependency graphs for augmenting Transformer language models. Unlike most previous work, GiLT does not insert extra structural tokens in language modeling; instead, it injects structural information into language modeling by modulating attention weights in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15562","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/2605.15562/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:35.260123Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.086069Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6c269212b94fb01bd2acd70051c51a5a7f8a87febdab595e8469937aa0c6e27c"},"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":"2605.15562","created_at":"2026-05-20T00:01:05.477295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15562v1","created_at":"2026-05-20T00:01:05.477295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15562","created_at":"2026-05-20T00:01:05.477295+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6JSGJ2NRVIM","created_at":"2026-05-20T00:01:05.477295+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6JSGJ2NRVIMRR2B","created_at":"2026-05-20T00:01:05.477295+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6JSGJ2N","created_at":"2026-05-20T00:01:05.477295+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/N6JSGJ2NRVIMRR2BTMLQOSMHIG","json":"https://pith.science/pith/N6JSGJ2NRVIMRR2BTMLQOSMHIG.json","graph_json":"https://pith.science/api/pith-number/N6JSGJ2NRVIMRR2BTMLQOSMHIG/graph.json","events_json":"https://pith.science/api/pith-number/N6JSGJ2NRVIMRR2BTMLQOSMHIG/events.json","paper":"https://pith.science/paper/N6JSGJ2N"},"agent_actions":{"view_html":"https://pith.science/pith/N6JSGJ2NRVIMRR2BTMLQOSMHIG","download_json":"https://pith.science/pith/N6JSGJ2NRVIMRR2BTMLQOSMHIG.json","view_paper":"https://pith.science/paper/N6JSGJ2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15562&json=true","fetch_graph":"https://pith.science/api/pith-number/N6JSGJ2NRVIMRR2BTMLQOSMHIG/graph.json","fetch_events":"https://pith.science/api/pith-number/N6JSGJ2NRVIMRR2BTMLQOSMHIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6JSGJ2NRVIMRR2BTMLQOSMHIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6JSGJ2NRVIMRR2BTMLQOSMHIG/action/storage_attestation","attest_author":"https://pith.science/pith/N6JSGJ2NRVIMRR2BTMLQOSMHIG/action/author_attestation","sign_citation":"https://pith.science/pith/N6JSGJ2NRVIMRR2BTMLQOSMHIG/action/citation_signature","submit_replication":"https://pith.science/pith/N6JSGJ2NRVIMRR2BTMLQOSMHIG/action/replication_record"}},"created_at":"2026-05-20T00:01:05.477295+00:00","updated_at":"2026-05-20T00:01:05.477295+00:00"}