{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L2ZXYMXBTZOIGGY2HDNJ56P2U3","short_pith_number":"pith:L2ZXYMXB","schema_version":"1.0","canonical_sha256":"5eb37c32e19e5c831b1a38da9ef9faa6fa1dc4f78bec44aca56a26e12a9daaa8","source":{"kind":"arxiv","id":"2501.15322","version":2},"attestation_state":"computed","paper":{"title":"Scaling laws for decoding images from brain activity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"primary_cat":"eess.IV","authors_text":"Hubert Banville, Jean-R\\'emi King, J\\'er\\'emy Rapin, St\\'ephane d'Ascoli, Yohann Benchetrit","submitted_at":"2025-01-25T20:38:36Z","abstract_excerpt":"Generative AI has recently propelled the decoding of images from brain activity. How do these approaches scale with the amount and type of neural recordings? Here, we systematically compare image decoding from four types of non-invasive devices: electroencephalography (EEG), magnetoencephalography (MEG), high-field functional Magnetic Resonance Imaging (3T fMRI) and ultra-high field (7T) fMRI. For this, we evaluate decoding models on the largest benchmark to date, encompassing 8 public datasets, 84 volunteers, 498 hours of brain recording and 2.3 million brain responses to natural images. Unli"},"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":"2501.15322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-01-25T20:38:36Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.NC"],"title_canon_sha256":"02febd996a75903e409c25ee1ea814b1c8d531633c3faa5f417d5f05e36ce186","abstract_canon_sha256":"131ca31d1baaebf1bc75e88caa85ff655408f57c5e6bc1434a0335be21136723"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:10.943051Z","signature_b64":"ItICkNVweE/FPB+94zycZS6+ckBCK/sZ11Jaxvu/66zMQnLZ5hk2eECYB9SY9PzzKuRxGjSz1vKSaNAmrpgiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eb37c32e19e5c831b1a38da9ef9faa6fa1dc4f78bec44aca56a26e12a9daaa8","last_reissued_at":"2026-07-05T10:06:10.942575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:10.942575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling laws for decoding images from brain activity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"primary_cat":"eess.IV","authors_text":"Hubert Banville, Jean-R\\'emi King, J\\'er\\'emy Rapin, St\\'ephane d'Ascoli, Yohann Benchetrit","submitted_at":"2025-01-25T20:38:36Z","abstract_excerpt":"Generative AI has recently propelled the decoding of images from brain activity. How do these approaches scale with the amount and type of neural recordings? Here, we systematically compare image decoding from four types of non-invasive devices: electroencephalography (EEG), magnetoencephalography (MEG), high-field functional Magnetic Resonance Imaging (3T fMRI) and ultra-high field (7T) fMRI. For this, we evaluate decoding models on the largest benchmark to date, encompassing 8 public datasets, 84 volunteers, 498 hours of brain recording and 2.3 million brain responses to natural images. Unli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15322","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.15322/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":"2501.15322","created_at":"2026-07-05T10:06:10.942643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15322v2","created_at":"2026-07-05T10:06:10.942643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15322","created_at":"2026-07-05T10:06:10.942643+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2ZXYMXBTZOI","created_at":"2026-07-05T10:06:10.942643+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2ZXYMXBTZOIGGY2","created_at":"2026-07-05T10:06:10.942643+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2ZXYMXB","created_at":"2026-07-05T10:06:10.942643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06345","citing_title":"Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18172","citing_title":"Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18172","citing_title":"Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09243","citing_title":"How Much is Brain Data Worth for Machine Learning?","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10688","citing_title":"DANCE: Detect and Classify Events in EEG","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08495","citing_title":"NeuralBench: A Unifying Framework to Benchmark NeuroAI Models","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04326","citing_title":"A foundation model of vision, audition, and language for in-silico neuroscience","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3","json":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3.json","graph_json":"https://pith.science/api/pith-number/L2ZXYMXBTZOIGGY2HDNJ56P2U3/graph.json","events_json":"https://pith.science/api/pith-number/L2ZXYMXBTZOIGGY2HDNJ56P2U3/events.json","paper":"https://pith.science/paper/L2ZXYMXB"},"agent_actions":{"view_html":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3","download_json":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3.json","view_paper":"https://pith.science/paper/L2ZXYMXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15322&json=true","fetch_graph":"https://pith.science/api/pith-number/L2ZXYMXBTZOIGGY2HDNJ56P2U3/graph.json","fetch_events":"https://pith.science/api/pith-number/L2ZXYMXBTZOIGGY2HDNJ56P2U3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3/action/storage_attestation","attest_author":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3/action/author_attestation","sign_citation":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3/action/citation_signature","submit_replication":"https://pith.science/pith/L2ZXYMXBTZOIGGY2HDNJ56P2U3/action/replication_record"}},"created_at":"2026-07-05T10:06:10.942643+00:00","updated_at":"2026-07-05T10:06:10.942643+00:00"}