{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PCVEPZLBCQPDT62K5UNFO2GZ6M","short_pith_number":"pith:PCVEPZLB","canonical_record":{"source":{"id":"2310.14509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T02:41:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"758de115dd0c3d5ee6a7ae544f4c2f2b294166de310ba6a52230d220072338c7","abstract_canon_sha256":"daad6daa8b66c74cffc91dd17c31dbb2e4fc4ec6d3950e6f9377bf204aca4bfa"},"schema_version":"1.0"},"canonical_sha256":"78aa47e561141e39fb4aed1a5768d9f321be5bb455493f130f142efd2d8368dc","source":{"kind":"arxiv","id":"2310.14509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14509","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14509v1","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14509","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"PCVEPZLBCQPD","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"PCVEPZLBCQPDT62K","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"PCVEPZLB","created_at":"2026-07-05T07:03:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PCVEPZLBCQPDT62K5UNFO2GZ6M","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T02:41:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"758de115dd0c3d5ee6a7ae544f4c2f2b294166de310ba6a52230d220072338c7","abstract_canon_sha256":"daad6daa8b66c74cffc91dd17c31dbb2e4fc4ec6d3950e6f9377bf204aca4bfa"},"schema_version":"1.0"},"canonical_sha256":"78aa47e561141e39fb4aed1a5768d9f321be5bb455493f130f142efd2d8368dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:45.539626Z","signature_b64":"H6UXzIIoAq1qRRhj7zYan8KL0Pivsye8wvqyEM+HWUsvobz1HrI3Gh0xjIqGxuTwP+JZT6XcuwBdEZQ8gJN+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78aa47e561141e39fb4aed1a5768d9f321be5bb455493f130f142efd2d8368dc","last_reissued_at":"2026-07-05T07:03:45.539209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:45.539209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14509","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":"2026-07-05T07:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DJVGSbwB6sU1Jofyzsp8A0VeULfPpkWLW7rKjd87scan718mWlME0CkMTtsojIqg8rEOZikgqUj/FBP1ynLMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:41:54.584536Z"},"content_sha256":"bbeabcf6467d5325906ca716381df173f42d847e47a77fb622a757f35daa0a80","schema_version":"1.0","event_id":"sha256:bbeabcf6467d5325906ca716381df173f42d847e47a77fb622a757f35daa0a80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PCVEPZLBCQPDT62K5UNFO2GZ6M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Iteratively Learn Diverse Strategies with State Distance Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingwei Li, Jingzhao Zhang, Sunli Chen, Wei Fu, Weihua Du, Yi Wu","submitted_at":"2023-10-23T02:41:34Z","abstract_excerpt":"In complex reinforcement learning (RL) problems, policies with similar rewards may have substantially different behaviors. It remains a fundamental challenge to optimize rewards while also discovering as many diverse strategies as possible, which can be crucial in many practical applications. Our study examines two design choices for tackling this challenge, i.e., diversity measure and computation framework. First, we find that with existing diversity measures, visually indistinguishable policies can still yield high diversity scores. To accurately capture the behavioral difference, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14509","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/2310.14509/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":"2026-07-05T07:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NXq7zH2+rVwqwHD0zaub38ttvb3jSqEhVUEXYzUxaoMrg9HeL8Xz7QWjLnhktb397hrw7HkXn+6dhkjwq6UdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:41:54.584915Z"},"content_sha256":"f72f679058b14b6c4ba66f17777949c0a3f499cc08f696d7ea9953775e3e333e","schema_version":"1.0","event_id":"sha256:f72f679058b14b6c4ba66f17777949c0a3f499cc08f696d7ea9953775e3e333e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCVEPZLBCQPDT62K5UNFO2GZ6M/bundle.json","state_url":"https://pith.science/pith/PCVEPZLBCQPDT62K5UNFO2GZ6M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCVEPZLBCQPDT62K5UNFO2GZ6M/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":"2026-07-06T09:41:54Z","links":{"resolver":"https://pith.science/pith/PCVEPZLBCQPDT62K5UNFO2GZ6M","bundle":"https://pith.science/pith/PCVEPZLBCQPDT62K5UNFO2GZ6M/bundle.json","state":"https://pith.science/pith/PCVEPZLBCQPDT62K5UNFO2GZ6M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCVEPZLBCQPDT62K5UNFO2GZ6M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PCVEPZLBCQPDT62K5UNFO2GZ6M","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":"daad6daa8b66c74cffc91dd17c31dbb2e4fc4ec6d3950e6f9377bf204aca4bfa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T02:41:34Z","title_canon_sha256":"758de115dd0c3d5ee6a7ae544f4c2f2b294166de310ba6a52230d220072338c7"},"schema_version":"1.0","source":{"id":"2310.14509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14509","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14509v1","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14509","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"PCVEPZLBCQPD","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"PCVEPZLBCQPDT62K","created_at":"2026-07-05T07:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"PCVEPZLB","created_at":"2026-07-05T07:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:f72f679058b14b6c4ba66f17777949c0a3f499cc08f696d7ea9953775e3e333e","target":"graph","created_at":"2026-07-05T07:03:45Z","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/2310.14509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In complex reinforcement learning (RL) problems, policies with similar rewards may have substantially different behaviors. It remains a fundamental challenge to optimize rewards while also discovering as many diverse strategies as possible, which can be crucial in many practical applications. Our study examines two design choices for tackling this challenge, i.e., diversity measure and computation framework. First, we find that with existing diversity measures, visually indistinguishable policies can still yield high diversity scores. To accurately capture the behavioral difference, we propose","authors_text":"Jingwei Li, Jingzhao Zhang, Sunli Chen, Wei Fu, Weihua Du, Yi Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T02:41:34Z","title":"Iteratively Learn Diverse Strategies with State Distance Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14509","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:bbeabcf6467d5325906ca716381df173f42d847e47a77fb622a757f35daa0a80","target":"record","created_at":"2026-07-05T07:03:45Z","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":"daad6daa8b66c74cffc91dd17c31dbb2e4fc4ec6d3950e6f9377bf204aca4bfa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T02:41:34Z","title_canon_sha256":"758de115dd0c3d5ee6a7ae544f4c2f2b294166de310ba6a52230d220072338c7"},"schema_version":"1.0","source":{"id":"2310.14509","kind":"arxiv","version":1}},"canonical_sha256":"78aa47e561141e39fb4aed1a5768d9f321be5bb455493f130f142efd2d8368dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78aa47e561141e39fb4aed1a5768d9f321be5bb455493f130f142efd2d8368dc","first_computed_at":"2026-07-05T07:03:45.539209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:45.539209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H6UXzIIoAq1qRRhj7zYan8KL0Pivsye8wvqyEM+HWUsvobz1HrI3Gh0xjIqGxuTwP+JZT6XcuwBdEZQ8gJN+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:45.539626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbeabcf6467d5325906ca716381df173f42d847e47a77fb622a757f35daa0a80","sha256:f72f679058b14b6c4ba66f17777949c0a3f499cc08f696d7ea9953775e3e333e"],"state_sha256":"cfbd42f732d8375e30b3ed7dd68312fcde7d6f0dc278599091c7032d8515e0a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dJ3/j2Cdlcosk0rSyp9e0QgE+nSK9P7JuTU0Zr+0gVoUwoJoSlniT3kn6mizKIzlqMcJsIwpoTIcgyai3Sn+Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T09:41:54.587006Z","bundle_sha256":"f08538f4d1711e13b3ed4268fda37a99008cea32d0cad921585241e3aa9bb7fb"}}