{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5YASPIORTRTIQY2SBUV372WZDT","short_pith_number":"pith:5YASPIOR","canonical_record":{"source":{"id":"2605.13665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T15:22:18Z","cross_cats_sorted":[],"title_canon_sha256":"0201fcdc2225428a118f75c873869a681480dd96b378cb6064b87e7fb652f5fa","abstract_canon_sha256":"a37a77f762a7c42656faac8478a885e43fdba7e735faf89cb324c80358cf7bae"},"schema_version":"1.0"},"canonical_sha256":"ee0127a1d19c668863520d2bbfead91cf64eb1709d17d13cbc079e436228129e","source":{"kind":"arxiv","id":"2605.13665","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13665","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13665v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13665","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"5YASPIORTRTI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5YASPIORTRTIQY2S","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5YASPIOR","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5YASPIORTRTIQY2SBUV372WZDT","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T15:22:18Z","cross_cats_sorted":[],"title_canon_sha256":"0201fcdc2225428a118f75c873869a681480dd96b378cb6064b87e7fb652f5fa","abstract_canon_sha256":"a37a77f762a7c42656faac8478a885e43fdba7e735faf89cb324c80358cf7bae"},"schema_version":"1.0"},"canonical_sha256":"ee0127a1d19c668863520d2bbfead91cf64eb1709d17d13cbc079e436228129e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:17.265312Z","signature_b64":"wQ2+zIXMgEuvqhmQnN6cbW2JQ/AhVV5vnJFGdFUreseCT+SNgLzZmdJCEjIIY8VvY/gubKMn1XFNEwwC3LvNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee0127a1d19c668863520d2bbfead91cf64eb1709d17d13cbc079e436228129e","last_reissued_at":"2026-05-18T02:44:17.264799Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:17.264799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13665","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":"2026-05-18T02:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xy790XIsuwi0QBJY3Wz/IIj2GSt87tx45znjxNDHsiBkMAHLRGCsRF748NsPdGYNUdKEPO8oPLKmIZ8/HKBICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:36:54.643284Z"},"content_sha256":"5a6b2d41602e644f242cca55697ad18b6bf2bc737aebf1ded25091904f4057fd","schema_version":"1.0","event_id":"sha256:5a6b2d41602e644f242cca55697ad18b6bf2bc737aebf1ded25091904f4057fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5YASPIORTRTIQY2SBUV372WZDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Quadruped robots learn to traverse narrow tunnels by distilling specialized policies from procedurally generated environments into one unified policy.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amir Hossain Raj, Dibyendu Das, Xuesu Xiao","submitted_at":"2026-05-13T15:22:18Z","abstract_excerpt":"Quadruped robots demonstrate exceptional potential for navigating complex terrain in critical applications such as search and rescue missions and infrastructure inspection However autonomous traversal of confined 3D environments including tunnels caves and collapsed structures remains a significant challenge Existing methods often struggle with rigid gait patterns limited adaptability to diverse geometries and reliance on oversimplified environmental assumptions This paper introduces a Reinforcement Learning RL framework that combines procedural environment generation with policy distillation "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By synthesizing diverse tunnel structures during training and distilling navigation strategies into a generalizable policy our method achieves consistent traversal across complex spatial constraints where conventional approaches fail.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that policies trained on procedurally generated tunnel geometries will transfer effectively to real-world tunnel configurations without further adaptation or domain randomization beyond what is described.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A teacher-student RL policy distillation approach combined with procedural tunnel generation enables quadruped robots to traverse narrow tunnels consistently in both simulation and real-world tests.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Quadruped robots learn to traverse narrow tunnels by distilling specialized policies from procedurally generated environments into one unified policy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b2a5c2a678eaad7c0421d1878b647bb27b491ddadbc8b48c695a3e8b11edc331"},"source":{"id":"2605.13665","kind":"arxiv","version":1},"verdict":{"id":"61c6efd3-e36c-4749-953e-6b72b60dbf85","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:16:47.757459Z","strongest_claim":"By synthesizing diverse tunnel structures during training and distilling navigation strategies into a generalizable policy our method achieves consistent traversal across complex spatial constraints where conventional approaches fail.","one_line_summary":"A teacher-student RL policy distillation approach combined with procedural tunnel generation enables quadruped robots to traverse narrow tunnels consistently in both simulation and real-world tests.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that policies trained on procedurally generated tunnel geometries will transfer effectively to real-world tunnel configurations without further adaptation or domain randomization beyond what is described.","pith_extraction_headline":"Quadruped robots learn to traverse narrow tunnels by distilling specialized policies from procedurally generated environments into one unified policy."},"references":{"count":26,"sample":[{"doi":"","year":2022,"title":"Learning to navigate sidewalks in outdoor environments,","work_id":"0bba638f-f9b2-48e1-a636-1cf7bbd9e85e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Bark- our: Benchmarking animal-level agility with quadruped robots.arXiv preprint arXiv:2305.14654, 2023","work_id":"5cbc4004-590c-4f29-af9d-f0ea6f6fe52b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Learning quadrupedal locomotion over challenging terrain,","work_id":"30be71ba-6fe1-48de-947b-a0cafce4d4fb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Rma: Rapid motor adaptation for legged robots","work_id":"6c62316f-7018-4586-9a12-d899b79f97ac","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Learning dynamic bipedal walking across stepping stones,","work_id":"64f1dcff-8e2a-4925-a7ca-17c44d385729","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":26,"snapshot_sha256":"1f59bd79e99a77dc9734905ae6d95aed9cd52510d99b81988b476170f0c2a97d","internal_anchors":1},"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":"61c6efd3-e36c-4749-953e-6b72b60dbf85"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYSGPzpNLgeLM2hdlixxy9ULVPTp3F89JjtQhdXrmdgDcq0bo3OryVNKena7BLN60AbLM8Lzbv9Htz8CsCmRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:36:54.644283Z"},"content_sha256":"a4f94af859ad2da54f438a5752e829ce0555c7c6f8b19c50a2dab26d83822135","schema_version":"1.0","event_id":"sha256:a4f94af859ad2da54f438a5752e829ce0555c7c6f8b19c50a2dab26d83822135"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YASPIORTRTIQY2SBUV372WZDT/bundle.json","state_url":"https://pith.science/pith/5YASPIORTRTIQY2SBUV372WZDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YASPIORTRTIQY2SBUV372WZDT/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":"2026-05-30T02:36:54Z","links":{"resolver":"https://pith.science/pith/5YASPIORTRTIQY2SBUV372WZDT","bundle":"https://pith.science/pith/5YASPIORTRTIQY2SBUV372WZDT/bundle.json","state":"https://pith.science/pith/5YASPIORTRTIQY2SBUV372WZDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YASPIORTRTIQY2SBUV372WZDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5YASPIORTRTIQY2SBUV372WZDT","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":"a37a77f762a7c42656faac8478a885e43fdba7e735faf89cb324c80358cf7bae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T15:22:18Z","title_canon_sha256":"0201fcdc2225428a118f75c873869a681480dd96b378cb6064b87e7fb652f5fa"},"schema_version":"1.0","source":{"id":"2605.13665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13665","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13665v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13665","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"5YASPIORTRTI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5YASPIORTRTIQY2S","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5YASPIOR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:a4f94af859ad2da54f438a5752e829ce0555c7c6f8b19c50a2dab26d83822135","target":"graph","created_at":"2026-05-18T02:44:17Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By synthesizing diverse tunnel structures during training and distilling navigation strategies into a generalizable policy our method achieves consistent traversal across complex spatial constraints where conventional approaches fail."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that policies trained on procedurally generated tunnel geometries will transfer effectively to real-world tunnel configurations without further adaptation or domain randomization beyond what is described."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A teacher-student RL policy distillation approach combined with procedural tunnel generation enables quadruped robots to traverse narrow tunnels consistently in both simulation and real-world tests."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Quadruped robots learn to traverse narrow tunnels by distilling specialized policies from procedurally generated environments into one unified policy."}],"snapshot_sha256":"b2a5c2a678eaad7c0421d1878b647bb27b491ddadbc8b48c695a3e8b11edc331"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Quadruped robots demonstrate exceptional potential for navigating complex terrain in critical applications such as search and rescue missions and infrastructure inspection However autonomous traversal of confined 3D environments including tunnels caves and collapsed structures remains a significant challenge Existing methods often struggle with rigid gait patterns limited adaptability to diverse geometries and reliance on oversimplified environmental assumptions This paper introduces a Reinforcement Learning RL framework that combines procedural environment generation with policy distillation ","authors_text":"Amir Hossain Raj, Dibyendu Das, Xuesu Xiao","cross_cats":[],"headline":"Quadruped robots learn to traverse narrow tunnels by distilling specialized policies from procedurally generated environments into one unified policy.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T15:22:18Z","title":"Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels"},"references":{"count":26,"internal_anchors":1,"resolved_work":26,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Learning to navigate sidewalks in outdoor environments,","work_id":"0bba638f-f9b2-48e1-a636-1cf7bbd9e85e","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Bark- our: Benchmarking animal-level agility with quadruped robots.arXiv preprint arXiv:2305.14654, 2023","work_id":"5cbc4004-590c-4f29-af9d-f0ea6f6fe52b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Learning quadrupedal locomotion over challenging terrain,","work_id":"30be71ba-6fe1-48de-947b-a0cafce4d4fb","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Rma: Rapid motor adaptation for legged robots","work_id":"6c62316f-7018-4586-9a12-d899b79f97ac","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Learning dynamic bipedal walking across stepping stones,","work_id":"64f1dcff-8e2a-4925-a7ca-17c44d385729","year":2022}],"snapshot_sha256":"1f59bd79e99a77dc9734905ae6d95aed9cd52510d99b81988b476170f0c2a97d"},"source":{"id":"2605.13665","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:16:47.757459Z","id":"61c6efd3-e36c-4749-953e-6b72b60dbf85","model_set":{"reader":"grok-4.3"},"one_line_summary":"A teacher-student RL policy distillation approach combined with procedural tunnel generation enables quadruped robots to traverse narrow tunnels consistently in both simulation and real-world tests.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Quadruped robots learn to traverse narrow tunnels by distilling specialized policies from procedurally generated environments into one unified policy.","strongest_claim":"By synthesizing diverse tunnel structures during training and distilling navigation strategies into a generalizable policy our method achieves consistent traversal across complex spatial constraints where conventional approaches fail.","weakest_assumption":"The assumption that policies trained on procedurally generated tunnel geometries will transfer effectively to real-world tunnel configurations without further adaptation or domain randomization beyond what is described."}},"verdict_id":"61c6efd3-e36c-4749-953e-6b72b60dbf85"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5a6b2d41602e644f242cca55697ad18b6bf2bc737aebf1ded25091904f4057fd","target":"record","created_at":"2026-05-18T02:44:17Z","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":"a37a77f762a7c42656faac8478a885e43fdba7e735faf89cb324c80358cf7bae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T15:22:18Z","title_canon_sha256":"0201fcdc2225428a118f75c873869a681480dd96b378cb6064b87e7fb652f5fa"},"schema_version":"1.0","source":{"id":"2605.13665","kind":"arxiv","version":1}},"canonical_sha256":"ee0127a1d19c668863520d2bbfead91cf64eb1709d17d13cbc079e436228129e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee0127a1d19c668863520d2bbfead91cf64eb1709d17d13cbc079e436228129e","first_computed_at":"2026-05-18T02:44:17.264799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:17.264799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wQ2+zIXMgEuvqhmQnN6cbW2JQ/AhVV5vnJFGdFUreseCT+SNgLzZmdJCEjIIY8VvY/gubKMn1XFNEwwC3LvNDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:17.265312Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a6b2d41602e644f242cca55697ad18b6bf2bc737aebf1ded25091904f4057fd","sha256:a4f94af859ad2da54f438a5752e829ce0555c7c6f8b19c50a2dab26d83822135"],"state_sha256":"efa535252425e9ec1f9d71b8f70abdafe411719efa79e489fe9c1e7784f36b63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wj7oqr6ae903gJgi6Hrv76BRzWU/PN97d7uuNy/Y9nVegNNmQN5rjc3JzIX4L2JuQroSVChiyZz6MrrsY/dQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T02:36:54.648293Z","bundle_sha256":"7106e8fd8f8350d9f049b2be52615d2d83d82f795bf6c11598c066b80f99df30"}}