{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6JAO2E7MDICLXN65KOJIZCS2O6","short_pith_number":"pith:6JAO2E7M","canonical_record":{"source":{"id":"2310.06214","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T00:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"5352de1879084e1f292ea73dcb404b75f86ad9f9beeaf41278ef0bf966f4965e","abstract_canon_sha256":"353cc1eb6d9c9f3090ca73e962b86d25fd2de1d125992bd3cd751f7b4fcfb859"},"schema_version":"1.0"},"canonical_sha256":"f240ed13ec1a04bbb7dd53928c8a5a77bd8a9e8cdef6a1b0364cc3a0408404a9","source":{"kind":"arxiv","id":"2310.06214","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06214","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06214v4","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06214","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"6JAO2E7MDICL","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"6JAO2E7MDICLXN65","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"6JAO2E7M","created_at":"2026-07-05T09:16:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6JAO2E7MDICLXN65KOJIZCS2O6","target":"record","payload":{"canonical_record":{"source":{"id":"2310.06214","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T00:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"5352de1879084e1f292ea73dcb404b75f86ad9f9beeaf41278ef0bf966f4965e","abstract_canon_sha256":"353cc1eb6d9c9f3090ca73e962b86d25fd2de1d125992bd3cd751f7b4fcfb859"},"schema_version":"1.0"},"canonical_sha256":"f240ed13ec1a04bbb7dd53928c8a5a77bd8a9e8cdef6a1b0364cc3a0408404a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:09.419605Z","signature_b64":"3hpYoOFwevqVZKj7VTnc8xHqiWRxUBFWrA/gvJ0kvScVgX8KZhw1nBWLDwIA1fnmfXLi9TinV2FuejskC6glAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f240ed13ec1a04bbb7dd53928c8a5a77bd8a9e8cdef6a1b0364cc3a0408404a9","last_reissued_at":"2026-07-05T09:16:09.419180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:09.419180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.06214","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QeEXfIH/4SFJQWNbL3f8HZisqG8QBwnh94rLQR8tQnkBpBi4fjjEHypfeM6CzpwIYtU4TqehRhtwAONUPyxKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:26:52.374045Z"},"content_sha256":"1e74c8df0f56ae2d0ae600d77e4b46603b27601b86b017103d923c8ed68a057d","schema_version":"1.0","event_id":"sha256:1e74c8df0f56ae2d0ae600d77e4b46603b27601b86b017103d923c8ed68a057d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6JAO2E7MDICLXN65KOJIZCS2O6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eslam Abdelrahman, Habib Slim, Mahmoud Ahmed, Mohamed Ayman, Mohamed Elhoseiny","submitted_at":"2023-10-10T00:07:25Z","abstract_excerpt":"3D visual grounding is the ability to localize objects in 3D scenes conditioned by utterances. Most existing methods devote the referring head to localize the referred object directly, causing failure in complex scenarios. In addition, it does not illustrate how and why the network reaches the final decision. In this paper, we address this question Can we design an interpretable 3D visual grounding framework that has the potential to mimic the human perception system?. To this end, we formulate the 3D visual grounding problem as a sequence-to-sequence Seq2Seq task by first predicting a chain o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06214","kind":"arxiv","version":4},"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/2310.06214/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":"2026-07-05T09:16:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZfEh/H1gYeM89/QsszNB3MuesEQ+epvXq81zZ9RY0bzvWaNccopvJNIUK7I0/lfyEmNjvPYkt/eyQwN0sqQ1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:26:52.374435Z"},"content_sha256":"7f54aa3f76116f6b3c4dbd6b015130aee261a05de2376a2c138a15a6664f0deb","schema_version":"1.0","event_id":"sha256:7f54aa3f76116f6b3c4dbd6b015130aee261a05de2376a2c138a15a6664f0deb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JAO2E7MDICLXN65KOJIZCS2O6/bundle.json","state_url":"https://pith.science/pith/6JAO2E7MDICLXN65KOJIZCS2O6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JAO2E7MDICLXN65KOJIZCS2O6/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":"2026-07-08T18:26:52Z","links":{"resolver":"https://pith.science/pith/6JAO2E7MDICLXN65KOJIZCS2O6","bundle":"https://pith.science/pith/6JAO2E7MDICLXN65KOJIZCS2O6/bundle.json","state":"https://pith.science/pith/6JAO2E7MDICLXN65KOJIZCS2O6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JAO2E7MDICLXN65KOJIZCS2O6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6JAO2E7MDICLXN65KOJIZCS2O6","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":"353cc1eb6d9c9f3090ca73e962b86d25fd2de1d125992bd3cd751f7b4fcfb859","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T00:07:25Z","title_canon_sha256":"5352de1879084e1f292ea73dcb404b75f86ad9f9beeaf41278ef0bf966f4965e"},"schema_version":"1.0","source":{"id":"2310.06214","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06214","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06214v4","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06214","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"6JAO2E7MDICL","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"6JAO2E7MDICLXN65","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"6JAO2E7M","created_at":"2026-07-05T09:16:09Z"}],"graph_snapshots":[{"event_id":"sha256:7f54aa3f76116f6b3c4dbd6b015130aee261a05de2376a2c138a15a6664f0deb","target":"graph","created_at":"2026-07-05T09:16:09Z","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/2310.06214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D visual grounding is the ability to localize objects in 3D scenes conditioned by utterances. Most existing methods devote the referring head to localize the referred object directly, causing failure in complex scenarios. In addition, it does not illustrate how and why the network reaches the final decision. In this paper, we address this question Can we design an interpretable 3D visual grounding framework that has the potential to mimic the human perception system?. To this end, we formulate the 3D visual grounding problem as a sequence-to-sequence Seq2Seq task by first predicting a chain o","authors_text":"Eslam Abdelrahman, Habib Slim, Mahmoud Ahmed, Mohamed Ayman, Mohamed Elhoseiny","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T00:07:25Z","title":"CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06214","kind":"arxiv","version":4},"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":"sha256:1e74c8df0f56ae2d0ae600d77e4b46603b27601b86b017103d923c8ed68a057d","target":"record","created_at":"2026-07-05T09:16:09Z","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":"353cc1eb6d9c9f3090ca73e962b86d25fd2de1d125992bd3cd751f7b4fcfb859","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T00:07:25Z","title_canon_sha256":"5352de1879084e1f292ea73dcb404b75f86ad9f9beeaf41278ef0bf966f4965e"},"schema_version":"1.0","source":{"id":"2310.06214","kind":"arxiv","version":4}},"canonical_sha256":"f240ed13ec1a04bbb7dd53928c8a5a77bd8a9e8cdef6a1b0364cc3a0408404a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f240ed13ec1a04bbb7dd53928c8a5a77bd8a9e8cdef6a1b0364cc3a0408404a9","first_computed_at":"2026-07-05T09:16:09.419180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:09.419180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3hpYoOFwevqVZKj7VTnc8xHqiWRxUBFWrA/gvJ0kvScVgX8KZhw1nBWLDwIA1fnmfXLi9TinV2FuejskC6glAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:09.419605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06214","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e74c8df0f56ae2d0ae600d77e4b46603b27601b86b017103d923c8ed68a057d","sha256:7f54aa3f76116f6b3c4dbd6b015130aee261a05de2376a2c138a15a6664f0deb"],"state_sha256":"6c525b3b38024ebc48487d50bae9b8ae3a5e98e4d4a18831eedd8acbfb246c3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"erQm7TE8BjRLLt7Qe95hRpTWWBNN2Jgk7oRCNOtFtv6xDJSlRVmJQ18vNQSIC9r+NwxDDbGEDphnia6/N/PCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T18:26:52.376456Z","bundle_sha256":"6bb2e0155b385138696adc41bac13276cc9e1de1b7c432b5e072d21096b54531"}}