{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UT5XCBCDRB4OAMEFY3CFPQ4NES","short_pith_number":"pith:UT5XCBCD","canonical_record":{"source":{"id":"2408.06926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T14:26:30Z","cross_cats_sorted":[],"title_canon_sha256":"e60e71b4249cae1f123a0a406fbf1d09b77aa2f9cd1756522729a96cec643d24","abstract_canon_sha256":"9b8907ac7e062b9b7e177385bacd804f745adde74b60f36ee6121e4279da68dc"},"schema_version":"1.0"},"canonical_sha256":"a4fb7104438878e03085c6c457c38d249edafb9564b768818d21e7b851f0b8ad","source":{"kind":"arxiv","id":"2408.06926","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06926","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06926v1","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06926","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"UT5XCBCDRB4O","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"pith_short_16","alias_value":"UT5XCBCDRB4OAMEF","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"pith_short_8","alias_value":"UT5XCBCD","created_at":"2026-07-05T08:55:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UT5XCBCDRB4OAMEFY3CFPQ4NES","target":"record","payload":{"canonical_record":{"source":{"id":"2408.06926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T14:26:30Z","cross_cats_sorted":[],"title_canon_sha256":"e60e71b4249cae1f123a0a406fbf1d09b77aa2f9cd1756522729a96cec643d24","abstract_canon_sha256":"9b8907ac7e062b9b7e177385bacd804f745adde74b60f36ee6121e4279da68dc"},"schema_version":"1.0"},"canonical_sha256":"a4fb7104438878e03085c6c457c38d249edafb9564b768818d21e7b851f0b8ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:03.793142Z","signature_b64":"fjsaZUqaCEFKFixvIyx7LcKZEHTtR8w7s78zskF6ycM/EYoej30uF9RTElPEvsGZd8uT5jHB1uQz7iWf3UGJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4fb7104438878e03085c6c457c38d249edafb9564b768818d21e7b851f0b8ad","last_reissued_at":"2026-07-05T08:55:03.792767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:03.792767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.06926","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":"2026-07-05T08:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6F0sLz3c1CiY3RE/Szs06DN7ysSzHBE/e0c1l+AR83ZF3FAuVvnXkni0NNO+G/Isk5q38gI/PEmCfy+QIF/uCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T03:40:06.710075Z"},"content_sha256":"8ff889900acedfb5263803d602ab4a4e9eed1217d1e61d53fa9dc4437049a7a4","schema_version":"1.0","event_id":"sha256:8ff889900acedfb5263803d602ab4a4e9eed1217d1e61d53fa9dc4437049a7a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UT5XCBCDRB4OAMEFY3CFPQ4NES","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SceneGPT: A Language Model for 3D Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shivam Chandhok","submitted_at":"2024-08-13T14:26:30Z","abstract_excerpt":"Building models that can understand and reason about 3D scenes is difficult owing to the lack of data sources for 3D supervised training and large-scale training regimes. In this work we ask - How can the knowledge in a pre-trained language model be leveraged for 3D scene understanding without any 3D pre-training. The aim of this work is to establish whether pre-trained LLMs possess priors/knowledge required for reasoning in 3D space and how can we prompt them such that they can be used for general purpose spatial reasoning and object understanding in 3D. To this end, we present SceneGPT, an L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06926","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/2408.06926/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":"2026-07-05T08:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"15PWzqF+WqsCGTHdl0hScLBWmVqhdwq5+qgd6DR8XFsCwtgnW7rz9eJWedzwfG4V9AZe64o6Mq9decyR+Pu3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T03:40:06.710452Z"},"content_sha256":"1ea78f2b8fcf5827a15309f57bf06fdc96b91b1cfe9e50f117191e4566b85fa5","schema_version":"1.0","event_id":"sha256:1ea78f2b8fcf5827a15309f57bf06fdc96b91b1cfe9e50f117191e4566b85fa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UT5XCBCDRB4OAMEFY3CFPQ4NES/bundle.json","state_url":"https://pith.science/pith/UT5XCBCDRB4OAMEFY3CFPQ4NES/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UT5XCBCDRB4OAMEFY3CFPQ4NES/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":"2026-07-21T03:40:06Z","links":{"resolver":"https://pith.science/pith/UT5XCBCDRB4OAMEFY3CFPQ4NES","bundle":"https://pith.science/pith/UT5XCBCDRB4OAMEFY3CFPQ4NES/bundle.json","state":"https://pith.science/pith/UT5XCBCDRB4OAMEFY3CFPQ4NES/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UT5XCBCDRB4OAMEFY3CFPQ4NES/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UT5XCBCDRB4OAMEFY3CFPQ4NES","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":"9b8907ac7e062b9b7e177385bacd804f745adde74b60f36ee6121e4279da68dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T14:26:30Z","title_canon_sha256":"e60e71b4249cae1f123a0a406fbf1d09b77aa2f9cd1756522729a96cec643d24"},"schema_version":"1.0","source":{"id":"2408.06926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06926","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06926v1","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06926","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"UT5XCBCDRB4O","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"pith_short_16","alias_value":"UT5XCBCDRB4OAMEF","created_at":"2026-07-05T08:55:03Z"},{"alias_kind":"pith_short_8","alias_value":"UT5XCBCD","created_at":"2026-07-05T08:55:03Z"}],"graph_snapshots":[{"event_id":"sha256:1ea78f2b8fcf5827a15309f57bf06fdc96b91b1cfe9e50f117191e4566b85fa5","target":"graph","created_at":"2026-07-05T08:55:03Z","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/2408.06926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building models that can understand and reason about 3D scenes is difficult owing to the lack of data sources for 3D supervised training and large-scale training regimes. In this work we ask - How can the knowledge in a pre-trained language model be leveraged for 3D scene understanding without any 3D pre-training. The aim of this work is to establish whether pre-trained LLMs possess priors/knowledge required for reasoning in 3D space and how can we prompt them such that they can be used for general purpose spatial reasoning and object understanding in 3D. To this end, we present SceneGPT, an L","authors_text":"Shivam Chandhok","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T14:26:30Z","title":"SceneGPT: A Language Model for 3D Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06926","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":"sha256:8ff889900acedfb5263803d602ab4a4e9eed1217d1e61d53fa9dc4437049a7a4","target":"record","created_at":"2026-07-05T08:55:03Z","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":"9b8907ac7e062b9b7e177385bacd804f745adde74b60f36ee6121e4279da68dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T14:26:30Z","title_canon_sha256":"e60e71b4249cae1f123a0a406fbf1d09b77aa2f9cd1756522729a96cec643d24"},"schema_version":"1.0","source":{"id":"2408.06926","kind":"arxiv","version":1}},"canonical_sha256":"a4fb7104438878e03085c6c457c38d249edafb9564b768818d21e7b851f0b8ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4fb7104438878e03085c6c457c38d249edafb9564b768818d21e7b851f0b8ad","first_computed_at":"2026-07-05T08:55:03.792767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:03.792767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fjsaZUqaCEFKFixvIyx7LcKZEHTtR8w7s78zskF6ycM/EYoej30uF9RTElPEvsGZd8uT5jHB1uQz7iWf3UGJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:03.793142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ff889900acedfb5263803d602ab4a4e9eed1217d1e61d53fa9dc4437049a7a4","sha256:1ea78f2b8fcf5827a15309f57bf06fdc96b91b1cfe9e50f117191e4566b85fa5"],"state_sha256":"30bef416fa35790017dab4531e7bc2e81b3acbed0f3e0d002c1e7563ed96af33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBeZCqb/fqFxcroRWU/voc9kh6WMmqXYaOdoQY9mjb1RbJc7n3oAUrJ2NGcBdW3yqFL9J9UQFAbJ/MUkiEA9AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T03:40:06.712683Z","bundle_sha256":"c7f2ef6c7f0d53705da2d5f4bcc11e8c84e6ed3397e7370e2f43510d5790ddab"}}