{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RFDC73ADD6CE2DVETR3GTCPX2F","short_pith_number":"pith:RFDC73AD","schema_version":"1.0","canonical_sha256":"89462fec031f844d0ea49c766989f7d17d849132bcfd62d858272068468c951e","source":{"kind":"arxiv","id":"1611.06928","version":1},"attestation_state":"computed","paper":{"title":"Memory Lens: How Much Memory Does an Agent Use?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Christoph Dann, Katja Hofmann, Sebastian Nowozin","submitted_at":"2016-11-21T18:22:27Z","abstract_excerpt":"We propose a new method to study the internal memory used by reinforcement learning policies. We estimate the amount of relevant past information by estimating mutual information between behavior histories and the current action of an agent. We perform this estimation in the passive setting, that is, we do not intervene but merely observe the natural behavior of the agent. Moreover, we provide a theoretical justification for our approach by showing that it yields an implementation-independent lower bound on the minimal memory capacity of any agent that implement the observed policy. We demonst"},"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":"1611.06928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T18:22:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"74062891a603fadff627446035c846794ba34f1384eda1e99199a0497fa9aad8","abstract_canon_sha256":"e5d5d617051841973fd376830a014d2b3a871faf5aabb752e139e599ff85e06f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:32.501889Z","signature_b64":"Wfo0V5A3SLoPgxCcnm0EQxtsuu/+dSawAy9QlSW8lDTYdOXY5wUim/98gXw+eD3yNXR387gc4NUSlgfVBYvOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89462fec031f844d0ea49c766989f7d17d849132bcfd62d858272068468c951e","last_reissued_at":"2026-05-18T00:57:32.501369Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:32.501369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Lens: How Much Memory Does an Agent Use?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Christoph Dann, Katja Hofmann, Sebastian Nowozin","submitted_at":"2016-11-21T18:22:27Z","abstract_excerpt":"We propose a new method to study the internal memory used by reinforcement learning policies. We estimate the amount of relevant past information by estimating mutual information between behavior histories and the current action of an agent. We perform this estimation in the passive setting, that is, we do not intervene but merely observe the natural behavior of the agent. Moreover, we provide a theoretical justification for our approach by showing that it yields an implementation-independent lower bound on the minimal memory capacity of any agent that implement the observed policy. We demonst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06928","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":""},"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":"1611.06928","created_at":"2026-05-18T00:57:32.501428+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06928v1","created_at":"2026-05-18T00:57:32.501428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06928","created_at":"2026-05-18T00:57:32.501428+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFDC73ADD6CE","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFDC73ADD6CE2DVE","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFDC73AD","created_at":"2026-05-18T12:30:41.710351+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/RFDC73ADD6CE2DVETR3GTCPX2F","json":"https://pith.science/pith/RFDC73ADD6CE2DVETR3GTCPX2F.json","graph_json":"https://pith.science/api/pith-number/RFDC73ADD6CE2DVETR3GTCPX2F/graph.json","events_json":"https://pith.science/api/pith-number/RFDC73ADD6CE2DVETR3GTCPX2F/events.json","paper":"https://pith.science/paper/RFDC73AD"},"agent_actions":{"view_html":"https://pith.science/pith/RFDC73ADD6CE2DVETR3GTCPX2F","download_json":"https://pith.science/pith/RFDC73ADD6CE2DVETR3GTCPX2F.json","view_paper":"https://pith.science/paper/RFDC73AD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06928&json=true","fetch_graph":"https://pith.science/api/pith-number/RFDC73ADD6CE2DVETR3GTCPX2F/graph.json","fetch_events":"https://pith.science/api/pith-number/RFDC73ADD6CE2DVETR3GTCPX2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFDC73ADD6CE2DVETR3GTCPX2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFDC73ADD6CE2DVETR3GTCPX2F/action/storage_attestation","attest_author":"https://pith.science/pith/RFDC73ADD6CE2DVETR3GTCPX2F/action/author_attestation","sign_citation":"https://pith.science/pith/RFDC73ADD6CE2DVETR3GTCPX2F/action/citation_signature","submit_replication":"https://pith.science/pith/RFDC73ADD6CE2DVETR3GTCPX2F/action/replication_record"}},"created_at":"2026-05-18T00:57:32.501428+00:00","updated_at":"2026-05-18T00:57:32.501428+00:00"}