{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UYZ3OXMCODXITZJN2GTFIAJLPL","short_pith_number":"pith:UYZ3OXMC","canonical_record":{"source":{"id":"2607.15935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-17T13:18:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f13a1a53b880409aaa80659d16f96a9b62ad894d1c050be27fe560ac9df962c9","abstract_canon_sha256":"83a47c0f880c589643ef4d9fd9f30a4704bb593aafdb83c7d95c2007a5471cc3"},"schema_version":"1.0"},"canonical_sha256":"a633b75d8270ee89e52dd1a654012b7ade66bbcf91f060796b22c4b04bd4a784","source":{"kind":"arxiv","id":"2607.15935","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15935","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15935v1","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15935","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"pith_short_12","alias_value":"UYZ3OXMCODXI","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"pith_short_16","alias_value":"UYZ3OXMCODXITZJN","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"pith_short_8","alias_value":"UYZ3OXMC","created_at":"2026-07-20T01:19:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UYZ3OXMCODXITZJN2GTFIAJLPL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-17T13:18:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f13a1a53b880409aaa80659d16f96a9b62ad894d1c050be27fe560ac9df962c9","abstract_canon_sha256":"83a47c0f880c589643ef4d9fd9f30a4704bb593aafdb83c7d95c2007a5471cc3"},"schema_version":"1.0"},"canonical_sha256":"a633b75d8270ee89e52dd1a654012b7ade66bbcf91f060796b22c4b04bd4a784","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:19:18.241828Z","signature_b64":"4lQDPc1PabXVcjiufrC1YnN4Qg1KwVp/Gx7h/vTw8OE22/lQBJJDyL2ZlsfkXtuGPpAnN/l7RrMjRHmj/hogBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a633b75d8270ee89e52dd1a654012b7ade66bbcf91f060796b22c4b04bd4a784","last_reissued_at":"2026-07-20T01:19:18.238908Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:19:18.238908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15935","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":"2026-07-20T01:19:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IuFtD03+4+1VJ7nmbgzTBpzfV3iweKJRXaKfx0CsaUgav9AeFosxy39Cn+kx5zjaPw/VPKjgFGyVGlwtO9BZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:01:09.396391Z"},"content_sha256":"da8db838ba57960709f7682b7854fe2043dc3ecbd16ac845fcf3e23bf67f1a74","schema_version":"1.0","event_id":"sha256:da8db838ba57960709f7682b7854fe2043dc3ecbd16ac845fcf3e23bf67f1a74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UYZ3OXMCODXITZJN2GTFIAJLPL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Jonas Weihing, Shahram Eivazi","submitted_at":"2026-07-17T13:18:32Z","abstract_excerpt":"Deep reinforcement learning (DRL) has a longstanding tradition in addressing the reach-avoid task problem, especially for controlling robotic arms. While this task serves as a baseline environment within the research community, the ability of DRL to effectively learn the each-avoid task in complex and realistic scenarios beyond simplified and restricted tabletop settings remains uncertain. In this paper, we present, for the first time, a comprehensive benchmark for the reachavoid task that accurately captures real-world complexities without simplifications. We demonstrate a diverse range of se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15935","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/2607.15935/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":"2026-07-20T01:19:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NTeR36s4EFdDLNABbDSN43+Z/6NFSDwn1xgPDWQotH560hfbRbNQI6Zt0Ij14XBiBxbGet+RtMfbPDCAbBOLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:01:09.396770Z"},"content_sha256":"f845c34ee8d584a7f8d0c1903b13a762e780eaf6e6e5f439cd64decaf7487b37","schema_version":"1.0","event_id":"sha256:f845c34ee8d584a7f8d0c1903b13a762e780eaf6e6e5f439cd64decaf7487b37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYZ3OXMCODXITZJN2GTFIAJLPL/bundle.json","state_url":"https://pith.science/pith/UYZ3OXMCODXITZJN2GTFIAJLPL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYZ3OXMCODXITZJN2GTFIAJLPL/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":"2026-08-05T03:01:09Z","links":{"resolver":"https://pith.science/pith/UYZ3OXMCODXITZJN2GTFIAJLPL","bundle":"https://pith.science/pith/UYZ3OXMCODXITZJN2GTFIAJLPL/bundle.json","state":"https://pith.science/pith/UYZ3OXMCODXITZJN2GTFIAJLPL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYZ3OXMCODXITZJN2GTFIAJLPL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UYZ3OXMCODXITZJN2GTFIAJLPL","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":"83a47c0f880c589643ef4d9fd9f30a4704bb593aafdb83c7d95c2007a5471cc3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-17T13:18:32Z","title_canon_sha256":"f13a1a53b880409aaa80659d16f96a9b62ad894d1c050be27fe560ac9df962c9"},"schema_version":"1.0","source":{"id":"2607.15935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15935","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15935v1","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15935","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"pith_short_12","alias_value":"UYZ3OXMCODXI","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"pith_short_16","alias_value":"UYZ3OXMCODXITZJN","created_at":"2026-07-20T01:19:18Z"},{"alias_kind":"pith_short_8","alias_value":"UYZ3OXMC","created_at":"2026-07-20T01:19:18Z"}],"graph_snapshots":[{"event_id":"sha256:f845c34ee8d584a7f8d0c1903b13a762e780eaf6e6e5f439cd64decaf7487b37","target":"graph","created_at":"2026-07-20T01:19:18Z","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/2607.15935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) has a longstanding tradition in addressing the reach-avoid task problem, especially for controlling robotic arms. While this task serves as a baseline environment within the research community, the ability of DRL to effectively learn the each-avoid task in complex and realistic scenarios beyond simplified and restricted tabletop settings remains uncertain. In this paper, we present, for the first time, a comprehensive benchmark for the reachavoid task that accurately captures real-world complexities without simplifications. We demonstrate a diverse range of se","authors_text":"Jonas Weihing, Shahram Eivazi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-17T13:18:32Z","title":"Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15935","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:da8db838ba57960709f7682b7854fe2043dc3ecbd16ac845fcf3e23bf67f1a74","target":"record","created_at":"2026-07-20T01:19:18Z","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":"83a47c0f880c589643ef4d9fd9f30a4704bb593aafdb83c7d95c2007a5471cc3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-17T13:18:32Z","title_canon_sha256":"f13a1a53b880409aaa80659d16f96a9b62ad894d1c050be27fe560ac9df962c9"},"schema_version":"1.0","source":{"id":"2607.15935","kind":"arxiv","version":1}},"canonical_sha256":"a633b75d8270ee89e52dd1a654012b7ade66bbcf91f060796b22c4b04bd4a784","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a633b75d8270ee89e52dd1a654012b7ade66bbcf91f060796b22c4b04bd4a784","first_computed_at":"2026-07-20T01:19:18.238908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T01:19:18.238908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4lQDPc1PabXVcjiufrC1YnN4Qg1KwVp/Gx7h/vTw8OE22/lQBJJDyL2ZlsfkXtuGPpAnN/l7RrMjRHmj/hogBw==","signature_status":"signed_v1","signed_at":"2026-07-20T01:19:18.241828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da8db838ba57960709f7682b7854fe2043dc3ecbd16ac845fcf3e23bf67f1a74","sha256:f845c34ee8d584a7f8d0c1903b13a762e780eaf6e6e5f439cd64decaf7487b37"],"state_sha256":"cf9c3b4c58e5a1aa7039db25c73072832684f3afaf3c40eabf3fd8b885328833"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdLgq1V1z/mQDn55mUq0cFeY8uKW+TmigYgUeKm1wiavCjBlkrCXk+11YmfeHwt0ERwKcRsRW5XdTQzZ8rpOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:01:09.399589Z","bundle_sha256":"d1c2e97d921c275485a53cff48ccd35b372f04206360433814e259182802d4da"}}