{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SC6OZQW35AQBXF5ADSOGF3VPJ6","short_pith_number":"pith:SC6OZQW3","canonical_record":{"source":{"id":"2509.15061","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-18T15:25:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5c755996a7ec37f70100d91fad119288f62679978f1d6b766121d31c59351e6a","abstract_canon_sha256":"c65adb535ab84f395fb4d1329c18c3774647b0abbd27cc5327dc1f749f0342f3"},"schema_version":"1.0"},"canonical_sha256":"90bcecc2dbe8201b97a01c9c62eeaf4f9f3ecb3a34303f79f987672ea7736700","source":{"kind":"arxiv","id":"2509.15061","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.15061","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"arxiv_version","alias_value":"2509.15061v2","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15061","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_12","alias_value":"SC6OZQW35AQB","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_16","alias_value":"SC6OZQW35AQBXF5A","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_8","alias_value":"SC6OZQW3","created_at":"2026-06-05T01:15:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SC6OZQW35AQBXF5ADSOGF3VPJ6","target":"record","payload":{"canonical_record":{"source":{"id":"2509.15061","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-18T15:25:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5c755996a7ec37f70100d91fad119288f62679978f1d6b766121d31c59351e6a","abstract_canon_sha256":"c65adb535ab84f395fb4d1329c18c3774647b0abbd27cc5327dc1f749f0342f3"},"schema_version":"1.0"},"canonical_sha256":"90bcecc2dbe8201b97a01c9c62eeaf4f9f3ecb3a34303f79f987672ea7736700","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:16.273640Z","signature_b64":"mY1unrPBRCKV8K5Y6oPJq5MU6O6+BifxHrEFo2S0vLs8/rbNN6xBN1mUlDThGclg0RDTQgctIWowSqv6sw0dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90bcecc2dbe8201b97a01c9c62eeaf4f9f3ecb3a34303f79f987672ea7736700","last_reissued_at":"2026-06-05T01:15:16.272823Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:16.272823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.15061","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaTlzhFvZvm4cUCCGnlPRVmzR2xSW2acsZhKMNHqXSOtk5tdnqmyQfHSm3TZMhZdCLJSEpqWJ8ks/5yDaSbGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T15:50:43.601884Z"},"content_sha256":"9625a8fc6ac7926478a9cf6c85575054979e910b063c2be1671ba149aacda376","schema_version":"1.0","event_id":"sha256:9625a8fc6ac7926478a9cf6c85575054979e910b063c2be1671ba149aacda376"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SC6OZQW35AQBXF5ADSOGF3VPJ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hui Zhang, Sicheng Xie, Tianyi Lu, Xinghao Zhu, Xingyao Lin, Xipeng Qiu, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2025-09-18T15:25:31Z","abstract_excerpt":"The ultimate goal of embodied agents is to create collaborators that can interact with humans, not mere executors that passively follow instructions. This requires agents to communicate, coordinate, and adapt their actions based on human feedback. Recently, advances in VLAs have offered a path toward this goal. However, most current VLA-based embodied agents operate in a one-way mode: they receive an instruction and execute it without feedback. This approach fails in real-world scenarios where instructions are often ambiguous. In this paper, we address this problem with the Ask-to-Clarify fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15061","kind":"arxiv","version":2},"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/2509.15061/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":"2026-06-05T01:15:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e9zGkI+xtQKtM7abPFpnqpwZwZgVD37o+Fw/lo3CJmhdH5SJLjLrJ9DO8332kB4QgaSEoBeQfePgynswSgCxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T15:50:43.602587Z"},"content_sha256":"7d978f1f58818e0b5366df45b6ee476c4f4c75b5f625b24ed8fcc1f8c70fa075","schema_version":"1.0","event_id":"sha256:7d978f1f58818e0b5366df45b6ee476c4f4c75b5f625b24ed8fcc1f8c70fa075"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SC6OZQW35AQBXF5ADSOGF3VPJ6/bundle.json","state_url":"https://pith.science/pith/SC6OZQW35AQBXF5ADSOGF3VPJ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SC6OZQW35AQBXF5ADSOGF3VPJ6/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":"2026-06-09T15:50:43Z","links":{"resolver":"https://pith.science/pith/SC6OZQW35AQBXF5ADSOGF3VPJ6","bundle":"https://pith.science/pith/SC6OZQW35AQBXF5ADSOGF3VPJ6/bundle.json","state":"https://pith.science/pith/SC6OZQW35AQBXF5ADSOGF3VPJ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SC6OZQW35AQBXF5ADSOGF3VPJ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SC6OZQW35AQBXF5ADSOGF3VPJ6","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":"c65adb535ab84f395fb4d1329c18c3774647b0abbd27cc5327dc1f749f0342f3","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-18T15:25:31Z","title_canon_sha256":"5c755996a7ec37f70100d91fad119288f62679978f1d6b766121d31c59351e6a"},"schema_version":"1.0","source":{"id":"2509.15061","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.15061","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"arxiv_version","alias_value":"2509.15061v2","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15061","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_12","alias_value":"SC6OZQW35AQB","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_16","alias_value":"SC6OZQW35AQBXF5A","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_8","alias_value":"SC6OZQW3","created_at":"2026-06-05T01:15:16Z"}],"graph_snapshots":[{"event_id":"sha256:7d978f1f58818e0b5366df45b6ee476c4f4c75b5f625b24ed8fcc1f8c70fa075","target":"graph","created_at":"2026-06-05T01:15:16Z","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/2509.15061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ultimate goal of embodied agents is to create collaborators that can interact with humans, not mere executors that passively follow instructions. This requires agents to communicate, coordinate, and adapt their actions based on human feedback. Recently, advances in VLAs have offered a path toward this goal. However, most current VLA-based embodied agents operate in a one-way mode: they receive an instruction and execute it without feedback. This approach fails in real-world scenarios where instructions are often ambiguous. In this paper, we address this problem with the Ask-to-Clarify fram","authors_text":"Hui Zhang, Sicheng Xie, Tianyi Lu, Xinghao Zhu, Xingyao Lin, Xipeng Qiu, Yu-Gang Jiang, Zuxuan Wu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-18T15:25:31Z","title":"Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15061","kind":"arxiv","version":2},"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":"sha256:9625a8fc6ac7926478a9cf6c85575054979e910b063c2be1671ba149aacda376","target":"record","created_at":"2026-06-05T01:15:16Z","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":"c65adb535ab84f395fb4d1329c18c3774647b0abbd27cc5327dc1f749f0342f3","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-18T15:25:31Z","title_canon_sha256":"5c755996a7ec37f70100d91fad119288f62679978f1d6b766121d31c59351e6a"},"schema_version":"1.0","source":{"id":"2509.15061","kind":"arxiv","version":2}},"canonical_sha256":"90bcecc2dbe8201b97a01c9c62eeaf4f9f3ecb3a34303f79f987672ea7736700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90bcecc2dbe8201b97a01c9c62eeaf4f9f3ecb3a34303f79f987672ea7736700","first_computed_at":"2026-06-05T01:15:16.272823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:16.272823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mY1unrPBRCKV8K5Y6oPJq5MU6O6+BifxHrEFo2S0vLs8/rbNN6xBN1mUlDThGclg0RDTQgctIWowSqv6sw0dBQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:16.273640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.15061","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9625a8fc6ac7926478a9cf6c85575054979e910b063c2be1671ba149aacda376","sha256:7d978f1f58818e0b5366df45b6ee476c4f4c75b5f625b24ed8fcc1f8c70fa075"],"state_sha256":"d00607bfcbf1027bc4de272ea517ba90c5c8b65d2d088b39d908bd92de66238d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nQqP3uzhW5dDwH3jksxTtFTtaBV6+iAIbcRXN/0pnhwzhuXTwNOdaRpA3urnkqn0klfxomVskJ4mnm2/tnFBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T15:50:43.606539Z","bundle_sha256":"ac65dc2f164f1bb49122ba532aec5534031c4c260c06292515fa50dbfb70943c"}}