{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FIDY6IBLVFGTHMAFPJOAGHU5IT","short_pith_number":"pith:FIDY6IBL","canonical_record":{"source":{"id":"2506.14495","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T13:17:31Z","cross_cats_sorted":[],"title_canon_sha256":"8e8880a48e37a32b554cb98dcdf10ea1042f3e6d3e479861505d8bf23c1aa267","abstract_canon_sha256":"683961d3e4053e957b5fc4006d70c8a822d346ad449c0c4ac33b13e1476f385d"},"schema_version":"1.0"},"canonical_sha256":"2a078f202ba94d33b0057a5c031e9d44d574bd7f802c89117b1d57badd53f488","source":{"kind":"arxiv","id":"2506.14495","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14495","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14495v1","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14495","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"FIDY6IBLVFGT","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"FIDY6IBLVFGTHMAF","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"FIDY6IBL","created_at":"2026-07-05T11:22:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FIDY6IBLVFGTHMAFPJOAGHU5IT","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14495","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T13:17:31Z","cross_cats_sorted":[],"title_canon_sha256":"8e8880a48e37a32b554cb98dcdf10ea1042f3e6d3e479861505d8bf23c1aa267","abstract_canon_sha256":"683961d3e4053e957b5fc4006d70c8a822d346ad449c0c4ac33b13e1476f385d"},"schema_version":"1.0"},"canonical_sha256":"2a078f202ba94d33b0057a5c031e9d44d574bd7f802c89117b1d57badd53f488","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:57.628943Z","signature_b64":"Klo6e59uJWpHTaq9qyFZdSOL5FKi0OwALKFOaU6uXCc1+0T6ZFvSVJmIpqYL2R5LvikqVzPmC3n6Wyvjrb9PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a078f202ba94d33b0057a5c031e9d44d574bd7f802c89117b1d57badd53f488","last_reissued_at":"2026-07-05T11:22:57.628465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:57.628465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14495","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":"2026-07-05T11:22:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PvIaAJivHCsZRRkzJ1mVVlH1o6kZiqaiFGT1Tp3PqQQQsTdxqxB4xc0m7hVSpVxDneTuKsiEMZaDwFOGAlZMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:20:29.564879Z"},"content_sha256":"f37dfca1c76e58c4f757eae5970fc859150d3583073426b00865527df5b92d24","schema_version":"1.0","event_id":"sha256:f37dfca1c76e58c4f757eae5970fc859150d3583073426b00865527df5b92d24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FIDY6IBLVFGTHMAFPJOAGHU5IT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"I Speak and You Find: Robust 3D Visual Grounding with Noisy and Ambiguous Speech Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honghua Chen, Liangliang Nan, Lipeng Gu, Mingqiang Wei, Yu Qi","submitted_at":"2025-06-17T13:17:31Z","abstract_excerpt":"Existing 3D visual grounding methods rely on precise text prompts to locate objects within 3D scenes. Speech, as a natural and intuitive modality, offers a promising alternative. Real-world speech inputs, however, often suffer from transcription errors due to accents, background noise, and varying speech rates, limiting the applicability of existing 3DVG methods. To address these challenges, we propose \\textbf{SpeechRefer}, a novel 3DVG framework designed to enhance performance in the presence of noisy and ambiguous speech-to-text transcriptions. SpeechRefer integrates seamlessly with xisting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14495","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/2506.14495/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":"2026-07-05T11:22:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9NoNjxgSo3BfdRosKbm/eiieBAbKp8imSwT/nA80woPHI/YFnI2PVrCTcYX9CWZEJO+KXIFCezZiUF2qg+0lBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:20:29.565261Z"},"content_sha256":"fd389ffa26f5a35db5e2429c6e0a799980cfaf1c7dc1d991abc6fd022d492367","schema_version":"1.0","event_id":"sha256:fd389ffa26f5a35db5e2429c6e0a799980cfaf1c7dc1d991abc6fd022d492367"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIDY6IBLVFGTHMAFPJOAGHU5IT/bundle.json","state_url":"https://pith.science/pith/FIDY6IBLVFGTHMAFPJOAGHU5IT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIDY6IBLVFGTHMAFPJOAGHU5IT/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":"2026-07-09T04:20:29Z","links":{"resolver":"https://pith.science/pith/FIDY6IBLVFGTHMAFPJOAGHU5IT","bundle":"https://pith.science/pith/FIDY6IBLVFGTHMAFPJOAGHU5IT/bundle.json","state":"https://pith.science/pith/FIDY6IBLVFGTHMAFPJOAGHU5IT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIDY6IBLVFGTHMAFPJOAGHU5IT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FIDY6IBLVFGTHMAFPJOAGHU5IT","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":"683961d3e4053e957b5fc4006d70c8a822d346ad449c0c4ac33b13e1476f385d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T13:17:31Z","title_canon_sha256":"8e8880a48e37a32b554cb98dcdf10ea1042f3e6d3e479861505d8bf23c1aa267"},"schema_version":"1.0","source":{"id":"2506.14495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14495","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14495v1","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14495","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"FIDY6IBLVFGT","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"FIDY6IBLVFGTHMAF","created_at":"2026-07-05T11:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"FIDY6IBL","created_at":"2026-07-05T11:22:57Z"}],"graph_snapshots":[{"event_id":"sha256:fd389ffa26f5a35db5e2429c6e0a799980cfaf1c7dc1d991abc6fd022d492367","target":"graph","created_at":"2026-07-05T11:22:57Z","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/2506.14495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing 3D visual grounding methods rely on precise text prompts to locate objects within 3D scenes. Speech, as a natural and intuitive modality, offers a promising alternative. Real-world speech inputs, however, often suffer from transcription errors due to accents, background noise, and varying speech rates, limiting the applicability of existing 3DVG methods. To address these challenges, we propose \\textbf{SpeechRefer}, a novel 3DVG framework designed to enhance performance in the presence of noisy and ambiguous speech-to-text transcriptions. SpeechRefer integrates seamlessly with xisting ","authors_text":"Honghua Chen, Liangliang Nan, Lipeng Gu, Mingqiang Wei, Yu Qi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T13:17:31Z","title":"I Speak and You Find: Robust 3D Visual Grounding with Noisy and Ambiguous Speech Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14495","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:f37dfca1c76e58c4f757eae5970fc859150d3583073426b00865527df5b92d24","target":"record","created_at":"2026-07-05T11:22:57Z","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":"683961d3e4053e957b5fc4006d70c8a822d346ad449c0c4ac33b13e1476f385d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T13:17:31Z","title_canon_sha256":"8e8880a48e37a32b554cb98dcdf10ea1042f3e6d3e479861505d8bf23c1aa267"},"schema_version":"1.0","source":{"id":"2506.14495","kind":"arxiv","version":1}},"canonical_sha256":"2a078f202ba94d33b0057a5c031e9d44d574bd7f802c89117b1d57badd53f488","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a078f202ba94d33b0057a5c031e9d44d574bd7f802c89117b1d57badd53f488","first_computed_at":"2026-07-05T11:22:57.628465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:57.628465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Klo6e59uJWpHTaq9qyFZdSOL5FKi0OwALKFOaU6uXCc1+0T6ZFvSVJmIpqYL2R5LvikqVzPmC3n6Wyvjrb9PBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:57.628943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f37dfca1c76e58c4f757eae5970fc859150d3583073426b00865527df5b92d24","sha256:fd389ffa26f5a35db5e2429c6e0a799980cfaf1c7dc1d991abc6fd022d492367"],"state_sha256":"b42d8c160c6350cab0b110bb82985b36c67915dfc0e28574cd55431ffd6122f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdkXY+WcisPjlRwxUkdLdHlYgyxOEtTQRocxzR6W5x59pYg2FQ/VOFiIKS+Jsj9sM0bxn0Slqpd2jduN3bdnBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:20:29.568484Z","bundle_sha256":"e99be1442bb4b2d9832f8f8b1f22b49b2c63baa38df773d2e052ed533e07e04b"}}