{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GA4STADYULWBGXASQQUZ7QDTJV","short_pith_number":"pith:GA4STADY","canonical_record":{"source":{"id":"2607.12931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T16:04:41Z","cross_cats_sorted":[],"title_canon_sha256":"d99a5a48c6437be5936197d01485c4f5c85bda383605d5421bf62183af753929","abstract_canon_sha256":"917608c0161dbc9b87db07fa80fc9a95b6e4f9ae7767ec1fabbaeda7c9284adf"},"schema_version":"1.0"},"canonical_sha256":"3039298078a2ec135c1284299fc0734d613c992961e1f704c494b1d62df2ff1b","source":{"kind":"arxiv","id":"2607.12931","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12931","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12931v1","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12931","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"pith_short_12","alias_value":"GA4STADYULWB","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"pith_short_16","alias_value":"GA4STADYULWBGXAS","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"pith_short_8","alias_value":"GA4STADY","created_at":"2026-07-15T01:22:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GA4STADYULWBGXASQQUZ7QDTJV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.12931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T16:04:41Z","cross_cats_sorted":[],"title_canon_sha256":"d99a5a48c6437be5936197d01485c4f5c85bda383605d5421bf62183af753929","abstract_canon_sha256":"917608c0161dbc9b87db07fa80fc9a95b6e4f9ae7767ec1fabbaeda7c9284adf"},"schema_version":"1.0"},"canonical_sha256":"3039298078a2ec135c1284299fc0734d613c992961e1f704c494b1d62df2ff1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:22:25.909002Z","signature_b64":"Cjqc52RccOxXnKYxljBiRec7aPkxv4JPxvV4qfz3IIExiURNGcjggbponHAlBE2bkNZyCsN+KA+CdF87b7eyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3039298078a2ec135c1284299fc0734d613c992961e1f704c494b1d62df2ff1b","last_reissued_at":"2026-07-15T01:22:25.908146Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:22:25.908146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.12931","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":"2026-07-15T01:22:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzOR6vt0f5bIuRCfNkCVpzK1QLWBnXanvfOzqOPSeNeu8p6wdFj45xBe7mOmjzmIDIQd6OqTXgVII30TD2G9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:34:47.012751Z"},"content_sha256":"98bbcde537a845cbdd1c78f23994ef6291efdd6c2a203a777551dc5d5ff0f304","schema_version":"1.0","event_id":"sha256:98bbcde537a845cbdd1c78f23994ef6291efdd6c2a203a777551dc5d5ff0f304"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GA4STADYULWBGXASQQUZ7QDTJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dacheng Tao, Guozheng Ma, Haoyu Wang, Li Shen, Yilun Kong, Yunpeng Qing, Zhi Hou","submitted_at":"2026-07-14T16:04:41Z","abstract_excerpt":"Reinforcement Learning (RL) has demonstrated significant potential for improving Vision-Language-Action (VLA) models on complex manipulation tasks. However, its practical scalability remains severely limited by the substantial cost of environmental interactions. In this work, we first investigate the exploration stagnation bottleneck in current VLA-RL frameworks and reveal that trajectory diversity is fundamentally more important to sample efficiency than the sheer quantity of collected rollouts. Motivated by these insights, we introduce RL Exploration Token (ExToken), a simple yet general fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12931","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/2607.12931/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":"2026-07-15T01:22:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sYg/Y5m43miRDqY324z81p57GbaHryTnYklvVf8UA/1hLqO5AJpdOaGvYMyWAI+SIh5Y8hGISG8NXcIZGdo9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:34:47.013303Z"},"content_sha256":"80fe790380b35c307c2a6e023ad6ceceb8d43a57de45b9639c808d5ee5c3b909","schema_version":"1.0","event_id":"sha256:80fe790380b35c307c2a6e023ad6ceceb8d43a57de45b9639c808d5ee5c3b909"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GA4STADYULWBGXASQQUZ7QDTJV/bundle.json","state_url":"https://pith.science/pith/GA4STADYULWBGXASQQUZ7QDTJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GA4STADYULWBGXASQQUZ7QDTJV/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":"2026-08-03T18:34:47Z","links":{"resolver":"https://pith.science/pith/GA4STADYULWBGXASQQUZ7QDTJV","bundle":"https://pith.science/pith/GA4STADYULWBGXASQQUZ7QDTJV/bundle.json","state":"https://pith.science/pith/GA4STADYULWBGXASQQUZ7QDTJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GA4STADYULWBGXASQQUZ7QDTJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GA4STADYULWBGXASQQUZ7QDTJV","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":"917608c0161dbc9b87db07fa80fc9a95b6e4f9ae7767ec1fabbaeda7c9284adf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T16:04:41Z","title_canon_sha256":"d99a5a48c6437be5936197d01485c4f5c85bda383605d5421bf62183af753929"},"schema_version":"1.0","source":{"id":"2607.12931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12931","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12931v1","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12931","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"pith_short_12","alias_value":"GA4STADYULWB","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"pith_short_16","alias_value":"GA4STADYULWBGXAS","created_at":"2026-07-15T01:22:25Z"},{"alias_kind":"pith_short_8","alias_value":"GA4STADY","created_at":"2026-07-15T01:22:25Z"}],"graph_snapshots":[{"event_id":"sha256:80fe790380b35c307c2a6e023ad6ceceb8d43a57de45b9639c808d5ee5c3b909","target":"graph","created_at":"2026-07-15T01:22:25Z","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/2607.12931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has demonstrated significant potential for improving Vision-Language-Action (VLA) models on complex manipulation tasks. However, its practical scalability remains severely limited by the substantial cost of environmental interactions. In this work, we first investigate the exploration stagnation bottleneck in current VLA-RL frameworks and reveal that trajectory diversity is fundamentally more important to sample efficiency than the sheer quantity of collected rollouts. Motivated by these insights, we introduce RL Exploration Token (ExToken), a simple yet general fra","authors_text":"Dacheng Tao, Guozheng Ma, Haoyu Wang, Li Shen, Yilun Kong, Yunpeng Qing, Zhi Hou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T16:04:41Z","title":"ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12931","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":"sha256:98bbcde537a845cbdd1c78f23994ef6291efdd6c2a203a777551dc5d5ff0f304","target":"record","created_at":"2026-07-15T01:22:25Z","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":"917608c0161dbc9b87db07fa80fc9a95b6e4f9ae7767ec1fabbaeda7c9284adf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T16:04:41Z","title_canon_sha256":"d99a5a48c6437be5936197d01485c4f5c85bda383605d5421bf62183af753929"},"schema_version":"1.0","source":{"id":"2607.12931","kind":"arxiv","version":1}},"canonical_sha256":"3039298078a2ec135c1284299fc0734d613c992961e1f704c494b1d62df2ff1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3039298078a2ec135c1284299fc0734d613c992961e1f704c494b1d62df2ff1b","first_computed_at":"2026-07-15T01:22:25.908146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:22:25.908146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cjqc52RccOxXnKYxljBiRec7aPkxv4JPxvV4qfz3IIExiURNGcjggbponHAlBE2bkNZyCsN+KA+CdF87b7eyBQ==","signature_status":"signed_v1","signed_at":"2026-07-15T01:22:25.909002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.12931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98bbcde537a845cbdd1c78f23994ef6291efdd6c2a203a777551dc5d5ff0f304","sha256:80fe790380b35c307c2a6e023ad6ceceb8d43a57de45b9639c808d5ee5c3b909"],"state_sha256":"899d4b6e9a0205237cb206b2b8218049c4e76682200faf50d676d42adc89d518"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1G29tOAcMX9/bjmvg6JhhVAdR0ZuFnK+MLad7i4eLnqgiY3rNWdSj5FHgP5h1Yldg1mxlzkJUpEiXqN0OhWaBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:34:47.016703Z","bundle_sha256":"13c806d90c2572074aeb7a896017e72b5200d5f4af8fbd60e31eab4a2daa1614"}}