{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ECO7JWOUCNQPVOJRZ52TBIBELU","short_pith_number":"pith:ECO7JWOU","canonical_record":{"source":{"id":"2501.17842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:46:35Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"27c25f3a7a592c6a92a4d644e4255ff982f9c067f2a8673248fc4ce33466d485","abstract_canon_sha256":"0cc89c7d0a672b739222cc5688ec94632c10264e11285aa401e123f0e6b87cf7"},"schema_version":"1.0"},"canonical_sha256":"209df4d9d41360fab931cf7530a0245d20408545f15f06213dbd3e5d34f4bc17","source":{"kind":"arxiv","id":"2501.17842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17842","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17842v1","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17842","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_12","alias_value":"ECO7JWOUCNQP","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_16","alias_value":"ECO7JWOUCNQPVOJR","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_8","alias_value":"ECO7JWOU","created_at":"2026-07-05T10:06:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ECO7JWOUCNQPVOJRZ52TBIBELU","target":"record","payload":{"canonical_record":{"source":{"id":"2501.17842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:46:35Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"27c25f3a7a592c6a92a4d644e4255ff982f9c067f2a8673248fc4ce33466d485","abstract_canon_sha256":"0cc89c7d0a672b739222cc5688ec94632c10264e11285aa401e123f0e6b87cf7"},"schema_version":"1.0"},"canonical_sha256":"209df4d9d41360fab931cf7530a0245d20408545f15f06213dbd3e5d34f4bc17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:58.911140Z","signature_b64":"Y6esPeh0dHEMIfzQpbfnU9qwclyPVjjnohuE11kMSYmrwQ4DY4GbPIRYdg3r4sx116PJISgdo8jAv53l5x5ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"209df4d9d41360fab931cf7530a0245d20408545f15f06213dbd3e5d34f4bc17","last_reissued_at":"2026-07-05T10:06:58.910720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:58.910720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.17842","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":"2026-07-05T10:06:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9y6Ka22phmAVy6LJj859L5p5C1TMUYvPZlA12P/G+o6OvhUIh81y56Ap0/luas2o8JxtYTStP+FJNV78o5icAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:38:59.041156Z"},"content_sha256":"33878b8c37ccfe59dfd24b672967565af655a9a0a584a95df4cbb4cb9c319735","schema_version":"1.0","event_id":"sha256:33878b8c37ccfe59dfd24b672967565af655a9a0a584a95df4cbb4cb9c319735"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ECO7JWOUCNQPVOJRZ52TBIBELU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Byoung-Tak Zhang, Hyeonseo Yang, Junseok Park, Minsu Lee, Min Whoo Lee, Won-Seok Choi","submitted_at":"2025-01-29T18:46:35Z","abstract_excerpt":"Reinforcement learning (RL) agents often face challenges in balancing exploration and exploitation, particularly in environments where sparse or dense rewards bias learning. Biological systems, such as human toddlers, naturally navigate this balance by transitioning from free exploration with sparse rewards to goal-directed behavior guided by increasingly dense rewards. Inspired by this natural progression, we investigate the Toddler-Inspired Reward Transition in goal-oriented RL tasks. Our study focuses on transitioning from sparse to potential-based dense (S2D) rewards while preserving optim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17842","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/2501.17842/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":"2026-07-05T10:06:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NdH9SGhj9V5a88D5o+jgr9NQjfBzf918MVwjMHVf4nkk9KLeUg/sCVa3gC+gH6w8ImPtmWow6Gz+iTv2krLBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:38:59.041886Z"},"content_sha256":"1eef0b43a319856ea7b93cb2562f851d68137cd590d4e793379f85def078cc34","schema_version":"1.0","event_id":"sha256:1eef0b43a319856ea7b93cb2562f851d68137cd590d4e793379f85def078cc34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECO7JWOUCNQPVOJRZ52TBIBELU/bundle.json","state_url":"https://pith.science/pith/ECO7JWOUCNQPVOJRZ52TBIBELU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECO7JWOUCNQPVOJRZ52TBIBELU/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":"2026-08-11T03:38:59Z","links":{"resolver":"https://pith.science/pith/ECO7JWOUCNQPVOJRZ52TBIBELU","bundle":"https://pith.science/pith/ECO7JWOUCNQPVOJRZ52TBIBELU/bundle.json","state":"https://pith.science/pith/ECO7JWOUCNQPVOJRZ52TBIBELU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECO7JWOUCNQPVOJRZ52TBIBELU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ECO7JWOUCNQPVOJRZ52TBIBELU","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":"0cc89c7d0a672b739222cc5688ec94632c10264e11285aa401e123f0e6b87cf7","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:46:35Z","title_canon_sha256":"27c25f3a7a592c6a92a4d644e4255ff982f9c067f2a8673248fc4ce33466d485"},"schema_version":"1.0","source":{"id":"2501.17842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17842","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17842v1","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17842","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_12","alias_value":"ECO7JWOUCNQP","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_16","alias_value":"ECO7JWOUCNQPVOJR","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_8","alias_value":"ECO7JWOU","created_at":"2026-07-05T10:06:58Z"}],"graph_snapshots":[{"event_id":"sha256:1eef0b43a319856ea7b93cb2562f851d68137cd590d4e793379f85def078cc34","target":"graph","created_at":"2026-07-05T10:06:58Z","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/2501.17842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents often face challenges in balancing exploration and exploitation, particularly in environments where sparse or dense rewards bias learning. Biological systems, such as human toddlers, naturally navigate this balance by transitioning from free exploration with sparse rewards to goal-directed behavior guided by increasingly dense rewards. Inspired by this natural progression, we investigate the Toddler-Inspired Reward Transition in goal-oriented RL tasks. Our study focuses on transitioning from sparse to potential-based dense (S2D) rewards while preserving optim","authors_text":"Byoung-Tak Zhang, Hyeonseo Yang, Junseok Park, Minsu Lee, Min Whoo Lee, Won-Seok Choi","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:46:35Z","title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17842","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":"sha256:33878b8c37ccfe59dfd24b672967565af655a9a0a584a95df4cbb4cb9c319735","target":"record","created_at":"2026-07-05T10:06:58Z","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":"0cc89c7d0a672b739222cc5688ec94632c10264e11285aa401e123f0e6b87cf7","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:46:35Z","title_canon_sha256":"27c25f3a7a592c6a92a4d644e4255ff982f9c067f2a8673248fc4ce33466d485"},"schema_version":"1.0","source":{"id":"2501.17842","kind":"arxiv","version":1}},"canonical_sha256":"209df4d9d41360fab931cf7530a0245d20408545f15f06213dbd3e5d34f4bc17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"209df4d9d41360fab931cf7530a0245d20408545f15f06213dbd3e5d34f4bc17","first_computed_at":"2026-07-05T10:06:58.910720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:58.910720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y6esPeh0dHEMIfzQpbfnU9qwclyPVjjnohuE11kMSYmrwQ4DY4GbPIRYdg3r4sx116PJISgdo8jAv53l5x5ZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:58.911140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33878b8c37ccfe59dfd24b672967565af655a9a0a584a95df4cbb4cb9c319735","sha256:1eef0b43a319856ea7b93cb2562f851d68137cd590d4e793379f85def078cc34"],"state_sha256":"60c70129b7f353a4191cb66f8de52b63e53b5c7509aaa89dee8f5698b9703e83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2BV2CGMhCDYxYtTspjmeuQTPVPZMj8eYbxsBG0zG9pjZ2XRsc2lRt9mSM6ImQMpOrR057Qp2bdr/bJTxaYBBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:38:59.052916Z","bundle_sha256":"dc1029aacad70ebdb08ad551c00c1f62803655ab9fb1b6e56e034baea3c28b85"}}