{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GE64ZTCKYJSZBZ65TTZIUDXETA","short_pith_number":"pith:GE64ZTCK","schema_version":"1.0","canonical_sha256":"313dcccc4ac26590e7dd9cf28a0ee4980d4c07eef76f3060cea3471213ff689d","source":{"kind":"arxiv","id":"2507.21871","version":1},"attestation_state":"computed","paper":{"title":"Representations in vision and language converge in a shared, multidimensional space of perceived similarities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Adrien Doerig, Clayton Hickey, Ian Charest, Katerina Marie Simkova","submitted_at":"2025-07-29T14:42:31Z","abstract_excerpt":"Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and language are well predicted by semantic feature spaces obtained from large language models (LLMs). This raises the possibility that sensory systems converge in their inherent ability to transform their inputs onto shared, embedding-like representational space. However, it remains unclear how such a space manifests in human behaviour. To investigate this, sixty"},"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":"2507.21871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2025-07-29T14:42:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"71685cf555d8ea217d2020c636112221deeed3ebbc10ad1f8d6951714f2c96b6","abstract_canon_sha256":"3c9dbd494183e3461ab565ab967e081728c4156b8991c95ebeca9291a2057b72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:09.145703Z","signature_b64":"oVnzUxGQTi4HLUi+31Q/Av2eTd4cZ/JzEqoscJFzk2oRaFyDbBRxL49Y8HYb5+6JXCz5MWqX81slbgWHn6EXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"313dcccc4ac26590e7dd9cf28a0ee4980d4c07eef76f3060cea3471213ff689d","last_reissued_at":"2026-07-05T11:45:09.145167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:09.145167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representations in vision and language converge in a shared, multidimensional space of perceived similarities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Adrien Doerig, Clayton Hickey, Ian Charest, Katerina Marie Simkova","submitted_at":"2025-07-29T14:42:31Z","abstract_excerpt":"Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and language are well predicted by semantic feature spaces obtained from large language models (LLMs). This raises the possibility that sensory systems converge in their inherent ability to transform their inputs onto shared, embedding-like representational space. However, it remains unclear how such a space manifests in human behaviour. To investigate this, sixty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21871","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/2507.21871/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":"2507.21871","created_at":"2026-07-05T11:45:09.145229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21871v1","created_at":"2026-07-05T11:45:09.145229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21871","created_at":"2026-07-05T11:45:09.145229+00:00"},{"alias_kind":"pith_short_12","alias_value":"GE64ZTCKYJSZ","created_at":"2026-07-05T11:45:09.145229+00:00"},{"alias_kind":"pith_short_16","alias_value":"GE64ZTCKYJSZBZ65","created_at":"2026-07-05T11:45:09.145229+00:00"},{"alias_kind":"pith_short_8","alias_value":"GE64ZTCK","created_at":"2026-07-05T11:45:09.145229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18226","citing_title":"Disentangling the Factors of Convergence between Brains and Computer Vision Models","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA","json":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA.json","graph_json":"https://pith.science/api/pith-number/GE64ZTCKYJSZBZ65TTZIUDXETA/graph.json","events_json":"https://pith.science/api/pith-number/GE64ZTCKYJSZBZ65TTZIUDXETA/events.json","paper":"https://pith.science/paper/GE64ZTCK"},"agent_actions":{"view_html":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA","download_json":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA.json","view_paper":"https://pith.science/paper/GE64ZTCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21871&json=true","fetch_graph":"https://pith.science/api/pith-number/GE64ZTCKYJSZBZ65TTZIUDXETA/graph.json","fetch_events":"https://pith.science/api/pith-number/GE64ZTCKYJSZBZ65TTZIUDXETA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA/action/storage_attestation","attest_author":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA/action/author_attestation","sign_citation":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA/action/citation_signature","submit_replication":"https://pith.science/pith/GE64ZTCKYJSZBZ65TTZIUDXETA/action/replication_record"}},"created_at":"2026-07-05T11:45:09.145229+00:00","updated_at":"2026-07-05T11:45:09.145229+00:00"}