{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CHTHUQZN6QM2QBSKU34JE5N3ZF","short_pith_number":"pith:CHTHUQZN","schema_version":"1.0","canonical_sha256":"11e67a432df419a8064aa6f89275bbc9455a4c7d80c039514da8436ee495cf70","source":{"kind":"arxiv","id":"2105.08710","version":2},"attestation_state":"computed","paper":{"title":"Fast and Slow Learning of Recurrent Independent Mechanisms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Bernhard Sch\\\"olkopf, Kanika Madan, Nan Rosemary Ke, Yoshua Bengio","submitted_at":"2021-05-18T17:50:32Z","abstract_excerpt":"Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel combinations of existing pieces of knowledge. We hypothesize that such a decomposition of knowledge is particularly relevant for being able to generalize in a systematic manner to out-of-distribution changes. To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stati"},"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":"2105.08710","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-18T17:50:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1449140e212a014106025e5d139d3c97791d1e7ecc71c9bb9e811381f8a9dca4","abstract_canon_sha256":"093ab8b5778d95b3063c778eebfd54a4765444723b969e8a78853405ad653203"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:33.378988Z","signature_b64":"n250e9E/T41yVriAyExST0LmOC3cIA2wxEM4QyDLgL3DN9+Fyx5r5s9D08L4jQUTqPIuk00FG0GG7ay+6+CFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11e67a432df419a8064aa6f89275bbc9455a4c7d80c039514da8436ee495cf70","last_reissued_at":"2026-07-05T02:41:33.378586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:33.378586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Slow Learning of Recurrent Independent Mechanisms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Bernhard Sch\\\"olkopf, Kanika Madan, Nan Rosemary Ke, Yoshua Bengio","submitted_at":"2021-05-18T17:50:32Z","abstract_excerpt":"Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel combinations of existing pieces of knowledge. We hypothesize that such a decomposition of knowledge is particularly relevant for being able to generalize in a systematic manner to out-of-distribution changes. To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08710","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/2105.08710/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":"2105.08710","created_at":"2026-07-05T02:41:33.378643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08710v2","created_at":"2026-07-05T02:41:33.378643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08710","created_at":"2026-07-05T02:41:33.378643+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHTHUQZN6QM2","created_at":"2026-07-05T02:41:33.378643+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHTHUQZN6QM2QBSK","created_at":"2026-07-05T02:41:33.378643+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHTHUQZN","created_at":"2026-07-05T02:41:33.378643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25299","citing_title":"The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF","json":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF.json","graph_json":"https://pith.science/api/pith-number/CHTHUQZN6QM2QBSKU34JE5N3ZF/graph.json","events_json":"https://pith.science/api/pith-number/CHTHUQZN6QM2QBSKU34JE5N3ZF/events.json","paper":"https://pith.science/paper/CHTHUQZN"},"agent_actions":{"view_html":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF","download_json":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF.json","view_paper":"https://pith.science/paper/CHTHUQZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08710&json=true","fetch_graph":"https://pith.science/api/pith-number/CHTHUQZN6QM2QBSKU34JE5N3ZF/graph.json","fetch_events":"https://pith.science/api/pith-number/CHTHUQZN6QM2QBSKU34JE5N3ZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF/action/storage_attestation","attest_author":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF/action/author_attestation","sign_citation":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF/action/citation_signature","submit_replication":"https://pith.science/pith/CHTHUQZN6QM2QBSKU34JE5N3ZF/action/replication_record"}},"created_at":"2026-07-05T02:41:33.378643+00:00","updated_at":"2026-07-05T02:41:33.378643+00:00"}