{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JZL6BCZPS6L2CCMQZWFXLFBU3H","short_pith_number":"pith:JZL6BCZP","canonical_record":{"source":{"id":"2407.09247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-12T13:20:52Z","cross_cats_sorted":[],"title_canon_sha256":"ed2067dbe7a68f0e1a45e9232f5dfd15d7c25e4ce7eb84c0eb3b8f7bb14bfbb1","abstract_canon_sha256":"fc048e97556657e13738c9efe73332656a3c734bce7fd69a38a460c1298d1b2f"},"schema_version":"1.0"},"canonical_sha256":"4e57e08b2f9797a10990cd8b759434d9f25cc69b1daa00b73ee2cd1d44eca2fb","source":{"kind":"arxiv","id":"2407.09247","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09247","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09247v1","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09247","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_12","alias_value":"JZL6BCZPS6L2","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_16","alias_value":"JZL6BCZPS6L2CCMQ","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_8","alias_value":"JZL6BCZP","created_at":"2026-07-05T08:43:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JZL6BCZPS6L2CCMQZWFXLFBU3H","target":"record","payload":{"canonical_record":{"source":{"id":"2407.09247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-12T13:20:52Z","cross_cats_sorted":[],"title_canon_sha256":"ed2067dbe7a68f0e1a45e9232f5dfd15d7c25e4ce7eb84c0eb3b8f7bb14bfbb1","abstract_canon_sha256":"fc048e97556657e13738c9efe73332656a3c734bce7fd69a38a460c1298d1b2f"},"schema_version":"1.0"},"canonical_sha256":"4e57e08b2f9797a10990cd8b759434d9f25cc69b1daa00b73ee2cd1d44eca2fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:16.969971Z","signature_b64":"HHebbSzlSB55y2BNRcYH0FstEXl5d7mrfT0bTb+SZIxqjvJxumgcCPZBWrgWl1Z9dERf/Wfh3KVfJmwTX/btAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e57e08b2f9797a10990cd8b759434d9f25cc69b1daa00b73ee2cd1d44eca2fb","last_reissued_at":"2026-07-05T08:43:16.969555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:16.969555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.09247","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:43:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ann2xDefHByMK+Wtx1yzUWwhllk8vdg6s+Fwies6E7a+9YtUxV86AKTqFhIX49NhA+20CpFyV2mjUJNcRd+dBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:48:31.138468Z"},"content_sha256":"b995101bbcbcd47d279903606e249c4493d2266a13df959abfabdbf1bf05b61e","schema_version":"1.0","event_id":"sha256:b995101bbcbcd47d279903606e249c4493d2266a13df959abfabdbf1bf05b61e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JZL6BCZPS6L2CCMQZWFXLFBU3H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Intrinsic Motivation for Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Shen, Cong Wang, Xiang Zheng, Xingjun Ma","submitted_at":"2024-07-12T13:20:52Z","abstract_excerpt":"This paper investigates two fundamental problems that arise when utilizing Intrinsic Motivation (IM) for reinforcement learning in Reward-Free Pre-Training (RFPT) tasks and Exploration with Intrinsic Motivation (EIM) tasks: 1) how to design an effective intrinsic objective in RFPT tasks, and 2) how to reduce the bias introduced by the intrinsic objective in EIM tasks. Existing IM methods suffer from static skills, limited state coverage, sample inefficiency in RFPT tasks, and suboptimality in EIM tasks. To tackle these problems, we propose \\emph{Constrained Intrinsic Motivation (CIM)} for RFPT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09247","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/2407.09247/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":"2026-07-05T08:43:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ak8iTS8c8CbKOJDEUD/fzG3oayUaz1nI/aNb8QuzXuIYByTA4cDUmDUwvRiT9HwMrFtIUspSXRT3h1aTbOuLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:48:31.139001Z"},"content_sha256":"22fc876193b919d2098bc70edea51ba11e6da985d845f7bf562ae98512471de0","schema_version":"1.0","event_id":"sha256:22fc876193b919d2098bc70edea51ba11e6da985d845f7bf562ae98512471de0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JZL6BCZPS6L2CCMQZWFXLFBU3H/bundle.json","state_url":"https://pith.science/pith/JZL6BCZPS6L2CCMQZWFXLFBU3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JZL6BCZPS6L2CCMQZWFXLFBU3H/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":"2026-08-08T12:48:31Z","links":{"resolver":"https://pith.science/pith/JZL6BCZPS6L2CCMQZWFXLFBU3H","bundle":"https://pith.science/pith/JZL6BCZPS6L2CCMQZWFXLFBU3H/bundle.json","state":"https://pith.science/pith/JZL6BCZPS6L2CCMQZWFXLFBU3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JZL6BCZPS6L2CCMQZWFXLFBU3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JZL6BCZPS6L2CCMQZWFXLFBU3H","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":"fc048e97556657e13738c9efe73332656a3c734bce7fd69a38a460c1298d1b2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-12T13:20:52Z","title_canon_sha256":"ed2067dbe7a68f0e1a45e9232f5dfd15d7c25e4ce7eb84c0eb3b8f7bb14bfbb1"},"schema_version":"1.0","source":{"id":"2407.09247","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09247","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09247v1","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09247","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_12","alias_value":"JZL6BCZPS6L2","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_16","alias_value":"JZL6BCZPS6L2CCMQ","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_8","alias_value":"JZL6BCZP","created_at":"2026-07-05T08:43:16Z"}],"graph_snapshots":[{"event_id":"sha256:22fc876193b919d2098bc70edea51ba11e6da985d845f7bf562ae98512471de0","target":"graph","created_at":"2026-07-05T08:43:16Z","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/2407.09247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates two fundamental problems that arise when utilizing Intrinsic Motivation (IM) for reinforcement learning in Reward-Free Pre-Training (RFPT) tasks and Exploration with Intrinsic Motivation (EIM) tasks: 1) how to design an effective intrinsic objective in RFPT tasks, and 2) how to reduce the bias introduced by the intrinsic objective in EIM tasks. Existing IM methods suffer from static skills, limited state coverage, sample inefficiency in RFPT tasks, and suboptimality in EIM tasks. To tackle these problems, we propose \\emph{Constrained Intrinsic Motivation (CIM)} for RFPT","authors_text":"Chao Shen, Cong Wang, Xiang Zheng, Xingjun Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-12T13:20:52Z","title":"Constrained Intrinsic Motivation for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09247","kind":"arxiv","version":1},"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:b995101bbcbcd47d279903606e249c4493d2266a13df959abfabdbf1bf05b61e","target":"record","created_at":"2026-07-05T08:43:16Z","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":"fc048e97556657e13738c9efe73332656a3c734bce7fd69a38a460c1298d1b2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-12T13:20:52Z","title_canon_sha256":"ed2067dbe7a68f0e1a45e9232f5dfd15d7c25e4ce7eb84c0eb3b8f7bb14bfbb1"},"schema_version":"1.0","source":{"id":"2407.09247","kind":"arxiv","version":1}},"canonical_sha256":"4e57e08b2f9797a10990cd8b759434d9f25cc69b1daa00b73ee2cd1d44eca2fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e57e08b2f9797a10990cd8b759434d9f25cc69b1daa00b73ee2cd1d44eca2fb","first_computed_at":"2026-07-05T08:43:16.969555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:16.969555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HHebbSzlSB55y2BNRcYH0FstEXl5d7mrfT0bTb+SZIxqjvJxumgcCPZBWrgWl1Z9dERf/Wfh3KVfJmwTX/btAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:16.969971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09247","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b995101bbcbcd47d279903606e249c4493d2266a13df959abfabdbf1bf05b61e","sha256:22fc876193b919d2098bc70edea51ba11e6da985d845f7bf562ae98512471de0"],"state_sha256":"4b656f7fd0a5c929c47aa1ad91929e8224fe70fe27585d67cbd914231fde70d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OMjxD2phue8rliuvgfznHQwTtYv5JdrYqNy7eMap4H2Dy5DR+BQ534DFlDNqrulI6SwYgXBI8nSiLg8vFxJiDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:48:31.143469Z","bundle_sha256":"c6b150ed9ba227a3a4d503f58d864c96c1870eb924b65b64a446a2c273462560"}}