{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XT37AZWGD757C6QKDMKDJILOGB","short_pith_number":"pith:XT37AZWG","schema_version":"1.0","canonical_sha256":"bcf7f066c61ffbf17a0a1b1434a16e304be8d11f2c97bce6dc49533e168d8c05","source":{"kind":"arxiv","id":"1709.07871","version":2},"attestation_state":"computed","paper":{"title":"FiLM: Visual Reasoning with a General Conditioning Layer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin","submitted_at":"2017-09-22T17:54:12Z","abstract_excerpt":"We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art"},"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":"1709.07871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-22T17:54:12Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"66bba6772b492ec16d16e4a981fe725dc411cf86b0a35eecd952198d75075b27","abstract_canon_sha256":"4365dee1688ea8c773fcc7c19bfd52862af8a9aed3a9f1a9bdf2ab6558d2d956"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:43.204145Z","signature_b64":"uKMn9NGhdGtHu45Z7jh+NCx2n5NRO86joOBHvxFJ8S/17aoHk9k/i5qQdFQKqUUv99qO4qqwBH7Q118pWAroDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcf7f066c61ffbf17a0a1b1434a16e304be8d11f2c97bce6dc49533e168d8c05","last_reissued_at":"2026-05-18T00:27:43.203629Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:43.203629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FiLM: Visual Reasoning with a General Conditioning Layer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin","submitted_at":"2017-09-22T17:54:12Z","abstract_excerpt":"We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.07871","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1709.07871","created_at":"2026-05-18T00:27:43.203706+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.07871v2","created_at":"2026-05-18T00:27:43.203706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.07871","created_at":"2026-05-18T00:27:43.203706+00:00"},{"alias_kind":"pith_short_12","alias_value":"XT37AZWGD757","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"XT37AZWGD757C6QK","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"XT37AZWG","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"1907.10303","citing_title":"Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2602.23833","citing_title":"Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15418","citing_title":"A General Differentiable Ray-Wave Framework for Hybrid Refractive-Diffractive System Modeling and Optimization","ref_index":123,"is_internal_anchor":true},{"citing_arxiv_id":"2508.06614","citing_title":"Local Diffusion Models and Phases of Data Distributions","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2511.07571","citing_title":"Forecasting implied volatility surface with generative diffusion models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2601.15844","citing_title":"Radio-Interferometric Image Reconstruction with Denoising Diffusion Restoration Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08512","citing_title":"MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13296","citing_title":"Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26324","citing_title":"Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08512","citing_title":"MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23750","citing_title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08519","citing_title":"SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23750","citing_title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00244","citing_title":"Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06598","citing_title":"Train-Small Deploy-Large: Leveraging Diffusion-Based Multi-Robot Planning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06475","citing_title":"AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02575","citing_title":"Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB","json":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB.json","graph_json":"https://pith.science/api/pith-number/XT37AZWGD757C6QKDMKDJILOGB/graph.json","events_json":"https://pith.science/api/pith-number/XT37AZWGD757C6QKDMKDJILOGB/events.json","paper":"https://pith.science/paper/XT37AZWG"},"agent_actions":{"view_html":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB","download_json":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB.json","view_paper":"https://pith.science/paper/XT37AZWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.07871&json=true","fetch_graph":"https://pith.science/api/pith-number/XT37AZWGD757C6QKDMKDJILOGB/graph.json","fetch_events":"https://pith.science/api/pith-number/XT37AZWGD757C6QKDMKDJILOGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB/action/storage_attestation","attest_author":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB/action/author_attestation","sign_citation":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB/action/citation_signature","submit_replication":"https://pith.science/pith/XT37AZWGD757C6QKDMKDJILOGB/action/replication_record"}},"created_at":"2026-05-18T00:27:43.203706+00:00","updated_at":"2026-05-18T00:27:43.203706+00:00"}