{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:52F37ON6XPBYCHWWXIGEIGQHE2","short_pith_number":"pith:52F37ON6","schema_version":"1.0","canonical_sha256":"ee8bbfb9bebbc3811ed6ba0c441a0726bb9573f733ea27d32fca23e711f76ce0","source":{"kind":"arxiv","id":"2204.08261","version":1},"attestation_state":"computed","paper":{"title":"Visio-Linguistic Brain Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Jashn Arora, Manish Gupta, Raju S. Bapi, Subba Reddy Oota, Vijay Rowtula","submitted_at":"2022-04-18T11:28:18Z","abstract_excerpt":"Enabling effective brain-computer interfaces requires understanding how the human brain encodes stimuli across modalities such as visual, language (or text), etc. Brain encoding aims at constructing fMRI brain activity given a stimulus. There exists a plethora of neural encoding models which study brain encoding for single mode stimuli: visual (pretrained CNNs) or text (pretrained language models). Few recent papers have also obtained separate visual and text representation models and performed late-fusion using simple heuristics. However, previous work has failed to explore: (a) the effective"},"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":"2204.08261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T11:28:18Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","q-bio.NC"],"title_canon_sha256":"6d2de30188dc5b6eed26d1f61f538f7ba73383768e33f9dbb43b4a1a82c97020","abstract_canon_sha256":"d3f7f0177924206597f7762765afb79151bc724a260ac2eeef7a38c022aa39a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:24.039081Z","signature_b64":"E4YKVEymmOuZnaEDyVC+mtnEppTSUT3C+QHtFfi5/Bx+YWUTibBFUd5FROa4A3aM4zq2wrrYn+r1AnX8t4YaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee8bbfb9bebbc3811ed6ba0c441a0726bb9573f733ea27d32fca23e711f76ce0","last_reissued_at":"2026-07-05T04:15:24.038638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:24.038638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visio-Linguistic Brain Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Jashn Arora, Manish Gupta, Raju S. Bapi, Subba Reddy Oota, Vijay Rowtula","submitted_at":"2022-04-18T11:28:18Z","abstract_excerpt":"Enabling effective brain-computer interfaces requires understanding how the human brain encodes stimuli across modalities such as visual, language (or text), etc. Brain encoding aims at constructing fMRI brain activity given a stimulus. There exists a plethora of neural encoding models which study brain encoding for single mode stimuli: visual (pretrained CNNs) or text (pretrained language models). Few recent papers have also obtained separate visual and text representation models and performed late-fusion using simple heuristics. However, previous work has failed to explore: (a) the effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08261","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/2204.08261/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":"2204.08261","created_at":"2026-07-05T04:15:24.038697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08261v1","created_at":"2026-07-05T04:15:24.038697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08261","created_at":"2026-07-05T04:15:24.038697+00:00"},{"alias_kind":"pith_short_12","alias_value":"52F37ON6XPBY","created_at":"2026-07-05T04:15:24.038697+00:00"},{"alias_kind":"pith_short_16","alias_value":"52F37ON6XPBYCHWW","created_at":"2026-07-05T04:15:24.038697+00:00"},{"alias_kind":"pith_short_8","alias_value":"52F37ON6","created_at":"2026-07-05T04:15:24.038697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04326","citing_title":"A foundation model of vision, audition, and language for in-silico neuroscience","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2","json":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2.json","graph_json":"https://pith.science/api/pith-number/52F37ON6XPBYCHWWXIGEIGQHE2/graph.json","events_json":"https://pith.science/api/pith-number/52F37ON6XPBYCHWWXIGEIGQHE2/events.json","paper":"https://pith.science/paper/52F37ON6"},"agent_actions":{"view_html":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2","download_json":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2.json","view_paper":"https://pith.science/paper/52F37ON6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08261&json=true","fetch_graph":"https://pith.science/api/pith-number/52F37ON6XPBYCHWWXIGEIGQHE2/graph.json","fetch_events":"https://pith.science/api/pith-number/52F37ON6XPBYCHWWXIGEIGQHE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2/action/storage_attestation","attest_author":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2/action/author_attestation","sign_citation":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2/action/citation_signature","submit_replication":"https://pith.science/pith/52F37ON6XPBYCHWWXIGEIGQHE2/action/replication_record"}},"created_at":"2026-07-05T04:15:24.038697+00:00","updated_at":"2026-07-05T04:15:24.038697+00:00"}