{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:T6AXIAXN4QHLW4PY6E3G6LLYUW","short_pith_number":"pith:T6AXIAXN","canonical_record":{"source":{"id":"2009.12494","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T01:20:05Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"218360146fa1078032fcef0f9cdd09325732505ff507933d5d1e60efd7e5c06b","abstract_canon_sha256":"daf56b68ab74b612aaf9ede7deff347f9d70d9b5272e9145697f52be0bed5946"},"schema_version":"1.0"},"canonical_sha256":"9f817402ede40ebb71f8f1366f2d78a5a3ce82460d2492c68d987651f569bc2f","source":{"kind":"arxiv","id":"2009.12494","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12494","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12494v2","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12494","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"pith_short_12","alias_value":"T6AXIAXN4QHL","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"pith_short_16","alias_value":"T6AXIAXN4QHLW4PY","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"pith_short_8","alias_value":"T6AXIAXN","created_at":"2026-07-05T04:24:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:T6AXIAXN4QHLW4PY6E3G6LLYUW","target":"record","payload":{"canonical_record":{"source":{"id":"2009.12494","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T01:20:05Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"218360146fa1078032fcef0f9cdd09325732505ff507933d5d1e60efd7e5c06b","abstract_canon_sha256":"daf56b68ab74b612aaf9ede7deff347f9d70d9b5272e9145697f52be0bed5946"},"schema_version":"1.0"},"canonical_sha256":"9f817402ede40ebb71f8f1366f2d78a5a3ce82460d2492c68d987651f569bc2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:33.775386Z","signature_b64":"CT4k5usfpumowzBB0g0xgUZCDtR4qHmNBwODKHVW8O46NLimf8OZuwrsTeKM0KM7ZYScc1fFqvNsX2V74QLJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f817402ede40ebb71f8f1366f2d78a5a3ce82460d2492c68d987651f569bc2f","last_reissued_at":"2026-07-05T04:24:33.774815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:33.774815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.12494","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:24:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fHLOkQiROoXMoU0YMihn+UVbxCHpLbip11IyxFlT6HOCPhDaHV6F8jd6PRtAM0tzHOJJzqRfX5UkSXk+QmU1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:23:22.358790Z"},"content_sha256":"bd231293c90d44bdb05f25a0ab08a85b03673e3d68fa2673194ce3c7130cd8e7","schema_version":"1.0","event_id":"sha256:bd231293c90d44bdb05f25a0ab08a85b03673e3d68fa2673194ce3c7130cd8e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:T6AXIAXN4QHLW4PY6E3G6LLYUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEMI: Self-supervised Exploration via Multisensory Incongruity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hang Zhao, Jianren Wang, Ziwen Zhuang","submitted_at":"2020-09-26T01:20:05Z","abstract_excerpt":"Efficient exploration is a long-standing problem in reinforcement learning since extrinsic rewards are usually sparse or missing. A popular solution to this issue is to feed an agent with novelty signals as intrinsic rewards. In this work, we introduce SEMI, a self-supervised exploration policy by incentivizing the agent to maximize a new novelty signal: multisensory incongruity, which can be measured in two aspects, perception incongruity and action incongruity. The former represents the misalignment of the multisensory inputs, while the latter represents the variance of an agent's policies u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12494","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/2009.12494/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:24:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnocUV2SnXkDmwYK02iXjiQqlm4gCYVlbMZyF9ak0eIf+YTkKWtOIjyHGbG13KAdbmCzgd4qZbYVHD270sekBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:23:22.359374Z"},"content_sha256":"853884d83501b30a20cb29eab2daa44a2f8199d5a7a649027a851ec569f102a0","schema_version":"1.0","event_id":"sha256:853884d83501b30a20cb29eab2daa44a2f8199d5a7a649027a851ec569f102a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6AXIAXN4QHLW4PY6E3G6LLYUW/bundle.json","state_url":"https://pith.science/pith/T6AXIAXN4QHLW4PY6E3G6LLYUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6AXIAXN4QHLW4PY6E3G6LLYUW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T16:23:22Z","links":{"resolver":"https://pith.science/pith/T6AXIAXN4QHLW4PY6E3G6LLYUW","bundle":"https://pith.science/pith/T6AXIAXN4QHLW4PY6E3G6LLYUW/bundle.json","state":"https://pith.science/pith/T6AXIAXN4QHLW4PY6E3G6LLYUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6AXIAXN4QHLW4PY6E3G6LLYUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:T6AXIAXN4QHLW4PY6E3G6LLYUW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"daf56b68ab74b612aaf9ede7deff347f9d70d9b5272e9145697f52be0bed5946","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T01:20:05Z","title_canon_sha256":"218360146fa1078032fcef0f9cdd09325732505ff507933d5d1e60efd7e5c06b"},"schema_version":"1.0","source":{"id":"2009.12494","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12494","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12494v2","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12494","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"pith_short_12","alias_value":"T6AXIAXN4QHL","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"pith_short_16","alias_value":"T6AXIAXN4QHLW4PY","created_at":"2026-07-05T04:24:33Z"},{"alias_kind":"pith_short_8","alias_value":"T6AXIAXN","created_at":"2026-07-05T04:24:33Z"}],"graph_snapshots":[{"event_id":"sha256:853884d83501b30a20cb29eab2daa44a2f8199d5a7a649027a851ec569f102a0","target":"graph","created_at":"2026-07-05T04:24:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.12494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient exploration is a long-standing problem in reinforcement learning since extrinsic rewards are usually sparse or missing. A popular solution to this issue is to feed an agent with novelty signals as intrinsic rewards. In this work, we introduce SEMI, a self-supervised exploration policy by incentivizing the agent to maximize a new novelty signal: multisensory incongruity, which can be measured in two aspects, perception incongruity and action incongruity. The former represents the misalignment of the multisensory inputs, while the latter represents the variance of an agent's policies u","authors_text":"Hang Zhao, Jianren Wang, Ziwen Zhuang","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T01:20:05Z","title":"SEMI: Self-supervised Exploration via Multisensory Incongruity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12494","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bd231293c90d44bdb05f25a0ab08a85b03673e3d68fa2673194ce3c7130cd8e7","target":"record","created_at":"2026-07-05T04:24:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"daf56b68ab74b612aaf9ede7deff347f9d70d9b5272e9145697f52be0bed5946","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T01:20:05Z","title_canon_sha256":"218360146fa1078032fcef0f9cdd09325732505ff507933d5d1e60efd7e5c06b"},"schema_version":"1.0","source":{"id":"2009.12494","kind":"arxiv","version":2}},"canonical_sha256":"9f817402ede40ebb71f8f1366f2d78a5a3ce82460d2492c68d987651f569bc2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f817402ede40ebb71f8f1366f2d78a5a3ce82460d2492c68d987651f569bc2f","first_computed_at":"2026-07-05T04:24:33.774815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:33.774815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CT4k5usfpumowzBB0g0xgUZCDtR4qHmNBwODKHVW8O46NLimf8OZuwrsTeKM0KM7ZYScc1fFqvNsX2V74QLJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:33.775386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.12494","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd231293c90d44bdb05f25a0ab08a85b03673e3d68fa2673194ce3c7130cd8e7","sha256:853884d83501b30a20cb29eab2daa44a2f8199d5a7a649027a851ec569f102a0"],"state_sha256":"a8aeece06c25f41238e848190908ce1ca1a810a0515eecd6b004341fb129880d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VchVE6Lh4wj0QiunA6xBtSF5OC6LB57ELekQRyONSigub5FQ0V4rBHS4HKwEo0N2VFSXpXOB9PfLioR7mmBmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:23:22.391423Z","bundle_sha256":"d8a34b54d0e01a12df03613839d26907cf3d1814a97c5ab1d76f429d90693b39"}}