{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EYD3HC6T3UNRK66H4SAA3SNXRJ","short_pith_number":"pith:EYD3HC6T","schema_version":"1.0","canonical_sha256":"2607b38bd3dd1b157bc7e4800dc9b78a412bd7b37ad460e04f5b0acac695e2ba","source":{"kind":"arxiv","id":"2606.23345","version":1},"attestation_state":"computed","paper":{"title":"Abstract representational geometry supports inference in large language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yunan Zeng, Yuwang Wang","submitted_at":"2026-06-22T13:50:34Z","abstract_excerpt":"A defining feature of human intelligence is the ability to adapt to changing environments by inferring latent task structure from sparse observations. Neuroscientific research indicates that this capability relies on the hippocampus constructing abstract representations, expressed as low-dimensional, approximately orthogonal manifolds in neural state space. However, the internal mechanisms of large language models (LLMs) remain largely opaque, making it unclear whether they form comparable abstract representations or instead rely on task-specific statistical regularities when performing compar"},"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":"2606.23345","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T13:50:34Z","cross_cats_sorted":[],"title_canon_sha256":"8d526f91b378bb611aa9d3a4eb83674523f006d2265312f847bffd7e78984eac","abstract_canon_sha256":"84ee35bf82d6f5b5c8af537363a3a8e7ac2c2d597521ec460816d4cb5024198a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:17.401476Z","signature_b64":"9eF8JLuRpb1G8j5gnxn/lufkHx7lio5w6o7teXdil68USYSiUiBuhV1i8CntM6zSD/OR/YH0QZzohMG2P1+0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2607b38bd3dd1b157bc7e4800dc9b78a412bd7b37ad460e04f5b0acac695e2ba","last_reissued_at":"2026-06-23T03:14:17.401079Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:17.401079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Abstract representational geometry supports inference in large language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yunan Zeng, Yuwang Wang","submitted_at":"2026-06-22T13:50:34Z","abstract_excerpt":"A defining feature of human intelligence is the ability to adapt to changing environments by inferring latent task structure from sparse observations. Neuroscientific research indicates that this capability relies on the hippocampus constructing abstract representations, expressed as low-dimensional, approximately orthogonal manifolds in neural state space. However, the internal mechanisms of large language models (LLMs) remain largely opaque, making it unclear whether they form comparable abstract representations or instead rely on task-specific statistical regularities when performing compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23345","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/2606.23345/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":"2606.23345","created_at":"2026-06-23T03:14:17.401133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23345v1","created_at":"2026-06-23T03:14:17.401133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23345","created_at":"2026-06-23T03:14:17.401133+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYD3HC6T3UNR","created_at":"2026-06-23T03:14:17.401133+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYD3HC6T3UNRK66H","created_at":"2026-06-23T03:14:17.401133+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYD3HC6T","created_at":"2026-06-23T03:14:17.401133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ","json":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ.json","graph_json":"https://pith.science/api/pith-number/EYD3HC6T3UNRK66H4SAA3SNXRJ/graph.json","events_json":"https://pith.science/api/pith-number/EYD3HC6T3UNRK66H4SAA3SNXRJ/events.json","paper":"https://pith.science/paper/EYD3HC6T"},"agent_actions":{"view_html":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ","download_json":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ.json","view_paper":"https://pith.science/paper/EYD3HC6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23345&json=true","fetch_graph":"https://pith.science/api/pith-number/EYD3HC6T3UNRK66H4SAA3SNXRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EYD3HC6T3UNRK66H4SAA3SNXRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ/action/storage_attestation","attest_author":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ/action/author_attestation","sign_citation":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ/action/citation_signature","submit_replication":"https://pith.science/pith/EYD3HC6T3UNRK66H4SAA3SNXRJ/action/replication_record"}},"created_at":"2026-06-23T03:14:17.401133+00:00","updated_at":"2026-06-23T03:14:17.401133+00:00"}