{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K5VDY32D66QVAG7NEBC4JJ6HXN","short_pith_number":"pith:K5VDY32D","schema_version":"1.0","canonical_sha256":"576a3c6f43f7a1501bed2045c4a7c7bb56de4cd3d53196253652315c310d019c","source":{"kind":"arxiv","id":"2501.15418","version":1},"attestation_state":"computed","paper":{"title":"Episodic Novelty Through Temporal Distance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Liang, Bo Xu, Chongjie Zhang, Dianyu Zhong, Hao Hu, Jun Yang, Qianchuan Zhao, Qihan Liu, Xiaoteng Ma, Yiqin Yang, Yuhua Jiang","submitted_at":"2025-01-26T06:43:45Z","abstract_excerpt":"Exploration in sparse reward environments remains a significant challenge in reinforcement learning, particularly in Contextual Markov Decision Processes (CMDPs), where environments differ across episodes. Existing episodic intrinsic motivation methods for CMDPs primarily rely on count-based approaches, which are ineffective in large state spaces, or on similarity-based methods that lack appropriate metrics for state comparison. To address these shortcomings, we propose Episodic Novelty Through Temporal Distance (ETD), a novel approach that introduces temporal distance as a robust metric for s"},"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":"2501.15418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-26T06:43:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"884649f74f74b194fc0fcb0ccc6c2e5603eb391b419721de88c7f1bc2dd9839e","abstract_canon_sha256":"d6d6beb4d041c0db62077b87ad2de3071c2adb7c290c5e353bc2fdd4894e1888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:28.992101Z","signature_b64":"vLP824rczjDDmSfgGT3ruP9rLg4pDTwfTxmPKzF4kpwh/iqpzJpkDt4q6zMrVCDQpltLhp1AQ0GAqtrfyLGVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"576a3c6f43f7a1501bed2045c4a7c7bb56de4cd3d53196253652315c310d019c","last_reissued_at":"2026-07-05T10:05:28.991586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:28.991586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Episodic Novelty Through Temporal Distance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Liang, Bo Xu, Chongjie Zhang, Dianyu Zhong, Hao Hu, Jun Yang, Qianchuan Zhao, Qihan Liu, Xiaoteng Ma, Yiqin Yang, Yuhua Jiang","submitted_at":"2025-01-26T06:43:45Z","abstract_excerpt":"Exploration in sparse reward environments remains a significant challenge in reinforcement learning, particularly in Contextual Markov Decision Processes (CMDPs), where environments differ across episodes. Existing episodic intrinsic motivation methods for CMDPs primarily rely on count-based approaches, which are ineffective in large state spaces, or on similarity-based methods that lack appropriate metrics for state comparison. To address these shortcomings, we propose Episodic Novelty Through Temporal Distance (ETD), a novel approach that introduces temporal distance as a robust metric for s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15418","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/2501.15418/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":"2501.15418","created_at":"2026-07-05T10:05:28.991652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15418v1","created_at":"2026-07-05T10:05:28.991652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15418","created_at":"2026-07-05T10:05:28.991652+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5VDY32D66QV","created_at":"2026-07-05T10:05:28.991652+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5VDY32D66QVAG7N","created_at":"2026-07-05T10:05:28.991652+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5VDY32D","created_at":"2026-07-05T10:05:28.991652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17933","citing_title":"AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25438","citing_title":"Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03201","citing_title":"SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN","json":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN.json","graph_json":"https://pith.science/api/pith-number/K5VDY32D66QVAG7NEBC4JJ6HXN/graph.json","events_json":"https://pith.science/api/pith-number/K5VDY32D66QVAG7NEBC4JJ6HXN/events.json","paper":"https://pith.science/paper/K5VDY32D"},"agent_actions":{"view_html":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN","download_json":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN.json","view_paper":"https://pith.science/paper/K5VDY32D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15418&json=true","fetch_graph":"https://pith.science/api/pith-number/K5VDY32D66QVAG7NEBC4JJ6HXN/graph.json","fetch_events":"https://pith.science/api/pith-number/K5VDY32D66QVAG7NEBC4JJ6HXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN/action/storage_attestation","attest_author":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN/action/author_attestation","sign_citation":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN/action/citation_signature","submit_replication":"https://pith.science/pith/K5VDY32D66QVAG7NEBC4JJ6HXN/action/replication_record"}},"created_at":"2026-07-05T10:05:28.991652+00:00","updated_at":"2026-07-05T10:05:28.991652+00:00"}