{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M7Y6GROMDKPL35XWLJYHRL6LST","short_pith_number":"pith:M7Y6GROM","canonical_record":{"source":{"id":"2503.10318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T12:53:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e01bc8ae832a9295e34413d37efc3f58d9442c4b45a6eb06e956691304fe0f14","abstract_canon_sha256":"db388e514a70ce41e14d376710fbda62e2077619509cec14a027a67bdda5097c"},"schema_version":"1.0"},"canonical_sha256":"67f1e345cc1a9ebdf6f65a7078afcb94e98123f872a5912132c4f1fa853e64a4","source":{"kind":"arxiv","id":"2503.10318","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10318","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10318v1","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10318","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"pith_short_12","alias_value":"M7Y6GROMDKPL","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"pith_short_16","alias_value":"M7Y6GROMDKPL35XW","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"pith_short_8","alias_value":"M7Y6GROM","created_at":"2026-07-05T10:54:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M7Y6GROMDKPL35XWLJYHRL6LST","target":"record","payload":{"canonical_record":{"source":{"id":"2503.10318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T12:53:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e01bc8ae832a9295e34413d37efc3f58d9442c4b45a6eb06e956691304fe0f14","abstract_canon_sha256":"db388e514a70ce41e14d376710fbda62e2077619509cec14a027a67bdda5097c"},"schema_version":"1.0"},"canonical_sha256":"67f1e345cc1a9ebdf6f65a7078afcb94e98123f872a5912132c4f1fa853e64a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:15.600917Z","signature_b64":"BFQW94ZPD1ZTanVvZKLmyJtRnkunpWaxWsA2Rf+SA6SUajsNVwJvVSCKnYL+RMM0KyouxVn+SZivoR8960NRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f1e345cc1a9ebdf6f65a7078afcb94e98123f872a5912132c4f1fa853e64a4","last_reissued_at":"2026-07-05T10:54:15.600420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:15.600420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.10318","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":"2026-07-05T10:54:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nvGs2wgl5MX1608VffdXNCIeR88G78tZxh85pMeDrdSpe7CHwyJofWxbnZrGAbP89yn7ghHYzCrwGMSeTcTYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:09:01.289296Z"},"content_sha256":"7eabf1da8a72137714f4bd8767a7cb987014dadbaf3f3221b1ba6d39e483feed","schema_version":"1.0","event_id":"sha256:7eabf1da8a72137714f4bd8767a7cb987014dadbaf3f3221b1ba6d39e483feed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M7Y6GROMDKPL35XWLJYHRL6LST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bang Giang Le, Duc Kien Doan, Viet Cuong Ta","submitted_at":"2025-03-13T12:53:42Z","abstract_excerpt":"In safe reinforcement learning, agent needs to balance between exploration actions and safety constraints. Following this paradigm, domain transfer approaches learn a prior Q-function from the related environments to prevent unsafe actions. However, because of the large number of false positives, some safe actions are never executed, leading to inadequate exploration in sparse-reward environments. In this work, we aim to learn an efficient state representation to balance the exploration and safety-prefer action in a sparse-reward environment. Firstly, the image input is mapped to latent repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10318","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/2503.10318/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":"2026-07-05T10:54:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hMyBR9QudAJN9Y6W9Xw45fv9jeuHyXkfmqYEw358JjgKILKnHRUQh5lYo3yzZ9u6PnwlcouaV8OE9dJ6sphjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:09:01.289806Z"},"content_sha256":"15b2c2df57c237def72bc241726e5a1e22fb7b9d3c20cbd46061c925e44d213c","schema_version":"1.0","event_id":"sha256:15b2c2df57c237def72bc241726e5a1e22fb7b9d3c20cbd46061c925e44d213c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7Y6GROMDKPL35XWLJYHRL6LST/bundle.json","state_url":"https://pith.science/pith/M7Y6GROMDKPL35XWLJYHRL6LST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7Y6GROMDKPL35XWLJYHRL6LST/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":"2026-08-22T07:09:01Z","links":{"resolver":"https://pith.science/pith/M7Y6GROMDKPL35XWLJYHRL6LST","bundle":"https://pith.science/pith/M7Y6GROMDKPL35XWLJYHRL6LST/bundle.json","state":"https://pith.science/pith/M7Y6GROMDKPL35XWLJYHRL6LST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7Y6GROMDKPL35XWLJYHRL6LST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M7Y6GROMDKPL35XWLJYHRL6LST","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":"db388e514a70ce41e14d376710fbda62e2077619509cec14a027a67bdda5097c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T12:53:42Z","title_canon_sha256":"e01bc8ae832a9295e34413d37efc3f58d9442c4b45a6eb06e956691304fe0f14"},"schema_version":"1.0","source":{"id":"2503.10318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10318","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10318v1","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10318","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"pith_short_12","alias_value":"M7Y6GROMDKPL","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"pith_short_16","alias_value":"M7Y6GROMDKPL35XW","created_at":"2026-07-05T10:54:15Z"},{"alias_kind":"pith_short_8","alias_value":"M7Y6GROM","created_at":"2026-07-05T10:54:15Z"}],"graph_snapshots":[{"event_id":"sha256:15b2c2df57c237def72bc241726e5a1e22fb7b9d3c20cbd46061c925e44d213c","target":"graph","created_at":"2026-07-05T10:54:15Z","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/2503.10318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In safe reinforcement learning, agent needs to balance between exploration actions and safety constraints. Following this paradigm, domain transfer approaches learn a prior Q-function from the related environments to prevent unsafe actions. However, because of the large number of false positives, some safe actions are never executed, leading to inadequate exploration in sparse-reward environments. In this work, we aim to learn an efficient state representation to balance the exploration and safety-prefer action in a sparse-reward environment. Firstly, the image input is mapped to latent repres","authors_text":"Bang Giang Le, Duc Kien Doan, Viet Cuong Ta","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T12:53:42Z","title":"Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10318","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":"sha256:7eabf1da8a72137714f4bd8767a7cb987014dadbaf3f3221b1ba6d39e483feed","target":"record","created_at":"2026-07-05T10:54:15Z","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":"db388e514a70ce41e14d376710fbda62e2077619509cec14a027a67bdda5097c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T12:53:42Z","title_canon_sha256":"e01bc8ae832a9295e34413d37efc3f58d9442c4b45a6eb06e956691304fe0f14"},"schema_version":"1.0","source":{"id":"2503.10318","kind":"arxiv","version":1}},"canonical_sha256":"67f1e345cc1a9ebdf6f65a7078afcb94e98123f872a5912132c4f1fa853e64a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67f1e345cc1a9ebdf6f65a7078afcb94e98123f872a5912132c4f1fa853e64a4","first_computed_at":"2026-07-05T10:54:15.600420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:15.600420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BFQW94ZPD1ZTanVvZKLmyJtRnkunpWaxWsA2Rf+SA6SUajsNVwJvVSCKnYL+RMM0KyouxVn+SZivoR8960NRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:15.600917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eabf1da8a72137714f4bd8767a7cb987014dadbaf3f3221b1ba6d39e483feed","sha256:15b2c2df57c237def72bc241726e5a1e22fb7b9d3c20cbd46061c925e44d213c"],"state_sha256":"31e5d59da0cf835384cd8431bc044d9a53a286a0c85750b3f06673de3a396819"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ZH2EsGR8/ZZmxDsBc+xzFdWUEQm2r1A6w1FbyWdfXw4BNzty1XuuDZqTCwc4BkEW/V4YfThCIdRC8ZKs/+MBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:09:01.294212Z","bundle_sha256":"3bccfc7b86c6e0180252c54831539a79d8e6fcf7fc359e2e981a49e19620ac66"}}