{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6MESLVPO2SWRXGM7SNQ34KVAGF","short_pith_number":"pith:6MESLVPO","schema_version":"1.0","canonical_sha256":"f30925d5eed4ad1b999f9361be2aa031572b2f0e968a1a0a9685970ff5ccfc95","source":{"kind":"arxiv","id":"2606.21075","version":1},"attestation_state":"computed","paper":{"title":"FiLM-Coordinated Dual-Branch Transformer for Global-Local Dependency Modeling in Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Junliang Dai, Xu Ling, Zhiqiang Zhou","submitted_at":"2026-06-19T03:48:49Z","abstract_excerpt":"Standard Transformers use a single self-attention pathway to model both global dependencies and local patterns, creating tension between long-range structural reasoning and fine-grained local representation learning. We propose a FiLM-coordinated dual-branch Transformer for language modeling, where each layer explicitly contains a global branch and a local branch, and feature-wise linear modulation (FiLM) is used for dynamic cross-branch coordination instead of simple concatenation or static addition. The key idea is that the two branches represent different dependency views of the same 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":"2606.21075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T03:48:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"327dc5bc9a90d99209db54bdc8725ffdbe813bf81b07e4f8e18e5a601f4886d1","abstract_canon_sha256":"eb517e1cfc3a4ebb2cbad058ade9b9f2c1c1b219edf6fd8aae9ca8962d50a74d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:29.020337Z","signature_b64":"6QMETsNckGyycN+Rdlr99NenLzWHHP2LVtQDQAQi1oDT6L9fybaFdXITAwsYLojHGUiHhflSSpB1A6MCWp7rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f30925d5eed4ad1b999f9361be2aa031572b2f0e968a1a0a9685970ff5ccfc95","last_reissued_at":"2026-06-23T01:12:29.019868Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:29.019868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FiLM-Coordinated Dual-Branch Transformer for Global-Local Dependency Modeling in Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Junliang Dai, Xu Ling, Zhiqiang Zhou","submitted_at":"2026-06-19T03:48:49Z","abstract_excerpt":"Standard Transformers use a single self-attention pathway to model both global dependencies and local patterns, creating tension between long-range structural reasoning and fine-grained local representation learning. We propose a FiLM-coordinated dual-branch Transformer for language modeling, where each layer explicitly contains a global branch and a local branch, and feature-wise linear modulation (FiLM) is used for dynamic cross-branch coordination instead of simple concatenation or static addition. The key idea is that the two branches represent different dependency views of the same input,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21075","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/2606.21075/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":"2606.21075","created_at":"2026-06-23T01:12:29.019942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21075v1","created_at":"2026-06-23T01:12:29.019942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21075","created_at":"2026-06-23T01:12:29.019942+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MESLVPO2SWR","created_at":"2026-06-23T01:12:29.019942+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MESLVPO2SWRXGM7","created_at":"2026-06-23T01:12:29.019942+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MESLVPO","created_at":"2026-06-23T01:12:29.019942+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/6MESLVPO2SWRXGM7SNQ34KVAGF","json":"https://pith.science/pith/6MESLVPO2SWRXGM7SNQ34KVAGF.json","graph_json":"https://pith.science/api/pith-number/6MESLVPO2SWRXGM7SNQ34KVAGF/graph.json","events_json":"https://pith.science/api/pith-number/6MESLVPO2SWRXGM7SNQ34KVAGF/events.json","paper":"https://pith.science/paper/6MESLVPO"},"agent_actions":{"view_html":"https://pith.science/pith/6MESLVPO2SWRXGM7SNQ34KVAGF","download_json":"https://pith.science/pith/6MESLVPO2SWRXGM7SNQ34KVAGF.json","view_paper":"https://pith.science/paper/6MESLVPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21075&json=true","fetch_graph":"https://pith.science/api/pith-number/6MESLVPO2SWRXGM7SNQ34KVAGF/graph.json","fetch_events":"https://pith.science/api/pith-number/6MESLVPO2SWRXGM7SNQ34KVAGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MESLVPO2SWRXGM7SNQ34KVAGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MESLVPO2SWRXGM7SNQ34KVAGF/action/storage_attestation","attest_author":"https://pith.science/pith/6MESLVPO2SWRXGM7SNQ34KVAGF/action/author_attestation","sign_citation":"https://pith.science/pith/6MESLVPO2SWRXGM7SNQ34KVAGF/action/citation_signature","submit_replication":"https://pith.science/pith/6MESLVPO2SWRXGM7SNQ34KVAGF/action/replication_record"}},"created_at":"2026-06-23T01:12:29.019942+00:00","updated_at":"2026-06-23T01:12:29.019942+00:00"}