{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IK2UM62ULOCRBMIFM24EHCTKF2","short_pith_number":"pith:IK2UM62U","schema_version":"1.0","canonical_sha256":"42b5467b545b8510b10566b8438a6a2ea7ff193df84c76d1bd488a115ba977ea","source":{"kind":"arxiv","id":"1906.12192","version":5},"attestation_state":"computed","paper":{"title":"GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marc Brockschmidt","submitted_at":"2019-06-28T13:07:22Z","abstract_excerpt":"This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing \"messages\" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an edge is additionally used to compute a transformation that can be applied to all incoming messages, allowing feature-wise modulation of the passed information.\n  Results of experiments comparing different GNN architectures on three tasks from the literature are presented, based "},"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":"1906.12192","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-28T13:07:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"21e117d3d0a61dcf09c8661e0300ce3599c25b8036ab3323423cac03bfb3f814","abstract_canon_sha256":"4d869ad3adf19f6ed01d96cdbd2949aaa8ed4fe619879da0534062b986ecc44c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:41.727249Z","signature_b64":"8nnCorFwDzUAmiqmwvsJDi2Mw9UfoYKSrZ5MCNpB5pIKJXsGBglUwyYu4e5pEOrRohdKVvKsvVlYkHVbmbw0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42b5467b545b8510b10566b8438a6a2ea7ff193df84c76d1bd488a115ba977ea","last_reissued_at":"2026-07-05T01:13:41.726803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:41.726803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marc Brockschmidt","submitted_at":"2019-06-28T13:07:22Z","abstract_excerpt":"This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing \"messages\" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an edge is additionally used to compute a transformation that can be applied to all incoming messages, allowing feature-wise modulation of the passed information.\n  Results of experiments comparing different GNN architectures on three tasks from the literature are presented, based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.12192","kind":"arxiv","version":5},"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/1906.12192/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":"1906.12192","created_at":"2026-07-05T01:13:41.726859+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.12192v5","created_at":"2026-07-05T01:13:41.726859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.12192","created_at":"2026-07-05T01:13:41.726859+00:00"},{"alias_kind":"pith_short_12","alias_value":"IK2UM62ULOCR","created_at":"2026-07-05T01:13:41.726859+00:00"},{"alias_kind":"pith_short_16","alias_value":"IK2UM62ULOCRBMIF","created_at":"2026-07-05T01:13:41.726859+00:00"},{"alias_kind":"pith_short_8","alias_value":"IK2UM62U","created_at":"2026-07-05T01:13:41.726859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16271","citing_title":"From Molecules to Mixtures: Learning Representations of Olfactory Mixture Similarity using Inductive Biases","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2","json":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2.json","graph_json":"https://pith.science/api/pith-number/IK2UM62ULOCRBMIFM24EHCTKF2/graph.json","events_json":"https://pith.science/api/pith-number/IK2UM62ULOCRBMIFM24EHCTKF2/events.json","paper":"https://pith.science/paper/IK2UM62U"},"agent_actions":{"view_html":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2","download_json":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2.json","view_paper":"https://pith.science/paper/IK2UM62U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.12192&json=true","fetch_graph":"https://pith.science/api/pith-number/IK2UM62ULOCRBMIFM24EHCTKF2/graph.json","fetch_events":"https://pith.science/api/pith-number/IK2UM62ULOCRBMIFM24EHCTKF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2/action/storage_attestation","attest_author":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2/action/author_attestation","sign_citation":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2/action/citation_signature","submit_replication":"https://pith.science/pith/IK2UM62ULOCRBMIFM24EHCTKF2/action/replication_record"}},"created_at":"2026-07-05T01:13:41.726859+00:00","updated_at":"2026-07-05T01:13:41.726859+00:00"}