{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NTG5QOQKGUJE4L2I57KBVGTB4M","short_pith_number":"pith:NTG5QOQK","schema_version":"1.0","canonical_sha256":"6ccdd83a0a35124e2f48efd41a9a61e3211480f0292f0e03a5bd6161ffa15434","source":{"kind":"arxiv","id":"1910.02227","version":2},"attestation_state":"computed","paper":{"title":"Making sense of sensory input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Johannes Welbl, Jose Hernandez-Orallo, Marek Sergot, Pushmeet Kohli, Richard Evans","submitted_at":"2019-10-05T07:48:55Z","abstract_excerpt":"This paper attempts to answer a central question in unsupervised learning: what does it mean to \"make sense\" of a sensory sequence? In our formalization, making sense involves constructing a symbolic causal theory that both explains the sensory sequence and also satisfies a set of unity conditions. The unity conditions insist that the constituents of the causal theory -- objects, properties, and laws -- must be integrated into a coherent whole. On our account, making sense of sensory input is a type of program synthesis, but it is unsupervised program synthesis.\n  Our second contribution is a "},"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":"1910.02227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-05T07:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"ccb41c0cad5c9b507734e797636487c5a59201fb140ea8f919b17ceda281f17f","abstract_canon_sha256":"851c7cfc8699da34363ced12557c17cdc6badec30171127116c003280f62a3bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:15.982023Z","signature_b64":"bbfLC78iyEHXSx2L8ZuzxUgdLHDCAjz0dT+0NU3oqDW4csnjA7PghnOAiVKlUqzmZgI4xrI4qmr6AU4XJiNsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ccdd83a0a35124e2f48efd41a9a61e3211480f0292f0e03a5bd6161ffa15434","last_reissued_at":"2026-07-05T01:18:15.981538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:15.981538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making sense of sensory input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Johannes Welbl, Jose Hernandez-Orallo, Marek Sergot, Pushmeet Kohli, Richard Evans","submitted_at":"2019-10-05T07:48:55Z","abstract_excerpt":"This paper attempts to answer a central question in unsupervised learning: what does it mean to \"make sense\" of a sensory sequence? In our formalization, making sense involves constructing a symbolic causal theory that both explains the sensory sequence and also satisfies a set of unity conditions. The unity conditions insist that the constituents of the causal theory -- objects, properties, and laws -- must be integrated into a coherent whole. On our account, making sense of sensory input is a type of program synthesis, but it is unsupervised program synthesis.\n  Our second contribution is a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02227","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/1910.02227/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":"1910.02227","created_at":"2026-07-05T01:18:15.981596+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.02227v2","created_at":"2026-07-05T01:18:15.981596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02227","created_at":"2026-07-05T01:18:15.981596+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTG5QOQKGUJE","created_at":"2026-07-05T01:18:15.981596+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTG5QOQKGUJE4L2I","created_at":"2026-07-05T01:18:15.981596+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTG5QOQK","created_at":"2026-07-05T01:18:15.981596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2206.04615","citing_title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M","json":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M.json","graph_json":"https://pith.science/api/pith-number/NTG5QOQKGUJE4L2I57KBVGTB4M/graph.json","events_json":"https://pith.science/api/pith-number/NTG5QOQKGUJE4L2I57KBVGTB4M/events.json","paper":"https://pith.science/paper/NTG5QOQK"},"agent_actions":{"view_html":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M","download_json":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M.json","view_paper":"https://pith.science/paper/NTG5QOQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.02227&json=true","fetch_graph":"https://pith.science/api/pith-number/NTG5QOQKGUJE4L2I57KBVGTB4M/graph.json","fetch_events":"https://pith.science/api/pith-number/NTG5QOQKGUJE4L2I57KBVGTB4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M/action/storage_attestation","attest_author":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M/action/author_attestation","sign_citation":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M/action/citation_signature","submit_replication":"https://pith.science/pith/NTG5QOQKGUJE4L2I57KBVGTB4M/action/replication_record"}},"created_at":"2026-07-05T01:18:15.981596+00:00","updated_at":"2026-07-05T01:18:15.981596+00:00"}