{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DTTDP7CTR2SCLKD6C7KQTO2S6T","short_pith_number":"pith:DTTDP7CT","canonical_record":{"source":{"id":"2109.10571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-22T08:06:42Z","cross_cats_sorted":[],"title_canon_sha256":"d442265d7b60dabd42c305cf55b0ca1940b37d2110343a4b59b17b03fcb9753a","abstract_canon_sha256":"e715d7b6870aeba4ed4aeeb1229fa3365bc2a98152c6cdfb26023276da883b81"},"schema_version":"1.0"},"canonical_sha256":"1ce637fc538ea425a87e17d509bb52f4e646333691e5b85c5913db6dab59edd7","source":{"kind":"arxiv","id":"2109.10571","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10571","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10571v1","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10571","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"DTTDP7CTR2SC","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"DTTDP7CTR2SCLKD6","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"DTTDP7CT","created_at":"2026-07-05T03:16:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DTTDP7CTR2SCLKD6C7KQTO2S6T","target":"record","payload":{"canonical_record":{"source":{"id":"2109.10571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-22T08:06:42Z","cross_cats_sorted":[],"title_canon_sha256":"d442265d7b60dabd42c305cf55b0ca1940b37d2110343a4b59b17b03fcb9753a","abstract_canon_sha256":"e715d7b6870aeba4ed4aeeb1229fa3365bc2a98152c6cdfb26023276da883b81"},"schema_version":"1.0"},"canonical_sha256":"1ce637fc538ea425a87e17d509bb52f4e646333691e5b85c5913db6dab59edd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:37.849389Z","signature_b64":"BqB0K9gi4m2jdZTnUS4ipsnbgcd+zeRm4JveGPUnvfAvp7KVSt0P33JCLX8gWtpDOEpcWKmfgTwS8lS+HsM+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ce637fc538ea425a87e17d509bb52f4e646333691e5b85c5913db6dab59edd7","last_reissued_at":"2026-07-05T03:16:37.848980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:37.848980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.10571","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":"2026-07-05T03:16:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9T45h1sKb56wN3HCa1dtQIOossOeWby84QXtHO4j3w0Qq/Mwo0V0hm3exm5vD7TqZUjyPIx2SQU4US/5yduXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:45:26.462140Z"},"content_sha256":"5fdc25841dd9be8327dc779de37414a857020499dbb13885e96add9c457164d0","schema_version":"1.0","event_id":"sha256:5fdc25841dd9be8327dc779de37414a857020499dbb13885e96add9c457164d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DTTDP7CTR2SCLKD6C7KQTO2S6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Grounding Referring Expression for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Di Guo, Fuchun Sun, Huaping Liu, Kaili Wang, Yefei Wang, Yi Wang","submitted_at":"2021-09-22T08:06:42Z","abstract_excerpt":"Referring expressions are commonly used when referring to a specific target in people's daily dialogue. In this paper, we develop a novel task of audio-visual grounding referring expression for robotic manipulation. The robot leverages both the audio and visual information to understand the referring expression in the given manipulation instruction and the corresponding manipulations are implemented. To solve the proposed task, an audio-visual framework is proposed for visual localization and sound recognition. We have also established a dataset which contains visual data, auditory data and ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10571","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/2109.10571/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":"2026-07-05T03:16:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OqAFs7QwSBdYfgC16v2F8szKi2XUbYmJevTrQ4hZqx1R0OJysqcHmgRhA/t+wnKxCv/eLplGGhjER9XDfqlKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:45:26.462655Z"},"content_sha256":"2c04df70fb45eb00d28b67c6d9d9adb0de567afdaa94537691a98f59aeb14e55","schema_version":"1.0","event_id":"sha256:2c04df70fb45eb00d28b67c6d9d9adb0de567afdaa94537691a98f59aeb14e55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DTTDP7CTR2SCLKD6C7KQTO2S6T/bundle.json","state_url":"https://pith.science/pith/DTTDP7CTR2SCLKD6C7KQTO2S6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DTTDP7CTR2SCLKD6C7KQTO2S6T/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":"2026-08-06T22:45:26Z","links":{"resolver":"https://pith.science/pith/DTTDP7CTR2SCLKD6C7KQTO2S6T","bundle":"https://pith.science/pith/DTTDP7CTR2SCLKD6C7KQTO2S6T/bundle.json","state":"https://pith.science/pith/DTTDP7CTR2SCLKD6C7KQTO2S6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DTTDP7CTR2SCLKD6C7KQTO2S6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DTTDP7CTR2SCLKD6C7KQTO2S6T","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":"e715d7b6870aeba4ed4aeeb1229fa3365bc2a98152c6cdfb26023276da883b81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-22T08:06:42Z","title_canon_sha256":"d442265d7b60dabd42c305cf55b0ca1940b37d2110343a4b59b17b03fcb9753a"},"schema_version":"1.0","source":{"id":"2109.10571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10571","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10571v1","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10571","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"DTTDP7CTR2SC","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"DTTDP7CTR2SCLKD6","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"DTTDP7CT","created_at":"2026-07-05T03:16:37Z"}],"graph_snapshots":[{"event_id":"sha256:2c04df70fb45eb00d28b67c6d9d9adb0de567afdaa94537691a98f59aeb14e55","target":"graph","created_at":"2026-07-05T03:16:37Z","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/2109.10571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring expressions are commonly used when referring to a specific target in people's daily dialogue. In this paper, we develop a novel task of audio-visual grounding referring expression for robotic manipulation. The robot leverages both the audio and visual information to understand the referring expression in the given manipulation instruction and the corresponding manipulations are implemented. To solve the proposed task, an audio-visual framework is proposed for visual localization and sound recognition. We have also established a dataset which contains visual data, auditory data and ma","authors_text":"Di Guo, Fuchun Sun, Huaping Liu, Kaili Wang, Yefei Wang, Yi Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-22T08:06:42Z","title":"Audio-Visual Grounding Referring Expression for Robotic Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10571","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":"sha256:5fdc25841dd9be8327dc779de37414a857020499dbb13885e96add9c457164d0","target":"record","created_at":"2026-07-05T03:16:37Z","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":"e715d7b6870aeba4ed4aeeb1229fa3365bc2a98152c6cdfb26023276da883b81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-22T08:06:42Z","title_canon_sha256":"d442265d7b60dabd42c305cf55b0ca1940b37d2110343a4b59b17b03fcb9753a"},"schema_version":"1.0","source":{"id":"2109.10571","kind":"arxiv","version":1}},"canonical_sha256":"1ce637fc538ea425a87e17d509bb52f4e646333691e5b85c5913db6dab59edd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ce637fc538ea425a87e17d509bb52f4e646333691e5b85c5913db6dab59edd7","first_computed_at":"2026-07-05T03:16:37.848980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:16:37.848980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BqB0K9gi4m2jdZTnUS4ipsnbgcd+zeRm4JveGPUnvfAvp7KVSt0P33JCLX8gWtpDOEpcWKmfgTwS8lS+HsM+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:16:37.849389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.10571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fdc25841dd9be8327dc779de37414a857020499dbb13885e96add9c457164d0","sha256:2c04df70fb45eb00d28b67c6d9d9adb0de567afdaa94537691a98f59aeb14e55"],"state_sha256":"860089b531e7ea25b0a847527a806e169e19b39374a2f850195db1d5c34cf70a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zBT0Ic0rIqeiZwmNv6Z75Z8HcW6qkW/Nm04wbroz2v6Nj0YGTyUxUP2uSOQ6sjwULvFe57+7X1aobFCcFnORAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:45:26.466346Z","bundle_sha256":"c1d06192fed27da7abd6d84f1771a726ca349aaf46a9c7ddb2cad14cdf344a63"}}