{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QJR3TPG7UYQUPKCXMZL56NQQJG","short_pith_number":"pith:QJR3TPG7","canonical_record":{"source":{"id":"2311.06612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T16:59:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ae27efc46f075999b9ab6f0b034dcac10cb40052250892e91d6dc6d2e9b10ff3","abstract_canon_sha256":"d7d5e73cb1a86903ddc3acea6a2bf69d5ba1297e916e8bf55af67dbd3c52cbc6"},"schema_version":"1.0"},"canonical_sha256":"8263b9bcdfa62147a8576657df3610498b99ce3aec500f10e0a247d77b7c5d30","source":{"kind":"arxiv","id":"2311.06612","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06612","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06612v1","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06612","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"QJR3TPG7UYQU","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"QJR3TPG7UYQUPKCX","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"QJR3TPG7","created_at":"2026-07-05T07:11:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QJR3TPG7UYQUPKCXMZL56NQQJG","target":"record","payload":{"canonical_record":{"source":{"id":"2311.06612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T16:59:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ae27efc46f075999b9ab6f0b034dcac10cb40052250892e91d6dc6d2e9b10ff3","abstract_canon_sha256":"d7d5e73cb1a86903ddc3acea6a2bf69d5ba1297e916e8bf55af67dbd3c52cbc6"},"schema_version":"1.0"},"canonical_sha256":"8263b9bcdfa62147a8576657df3610498b99ce3aec500f10e0a247d77b7c5d30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:42.816481Z","signature_b64":"RQ8/GwiPLzUWP8o4QjGGgDaek21MKCK6wYTDe9HMToWY4TZBwM8rUaybX4WHBRS6kNhfQbJz0H0pvsQdlIOxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8263b9bcdfa62147a8576657df3610498b99ce3aec500f10e0a247d77b7c5d30","last_reissued_at":"2026-07-05T07:11:42.815945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:42.815945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.06612","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":"2026-07-05T07:11:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rmxfo3/lwD2MiGajxhRQbvkdtChhYq4ArQWmZwjab1AW81U+0elnrGgc+GJTA7Wnb2YC0axez7V365XkfHOoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:28:45.096496Z"},"content_sha256":"532ce54ba04dcdd4b980d3d5e9b3aa681e6a790cb434d1a173ab51c20bee8a90","schema_version":"1.0","event_id":"sha256:532ce54ba04dcdd4b980d3d5e9b3aa681e6a790cb434d1a173ab51c20bee8a90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QJR3TPG7UYQUPKCXMZL56NQQJG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiahui Gao, Jipeng Zhang, Lewei Yao, Renjie Pi, Tong Zhang","submitted_at":"2023-11-11T16:59:20Z","abstract_excerpt":"The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate visual perception tasks remains a challenge. In this paper, we present a novel end-to-end framework named PerceptionGPT, which efficiently and effectively equips the VLLMs with visual perception abilities by leveraging the representation power of LLMs' token embedding. Our proposed method treats the token embedding of the LLM as the carrier of spatial informatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06612","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/2311.06612/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":"2026-07-05T07:11:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/cUiA1mVsSiAwZQ4+EopHLb/DQEZu3p3dUKBjhJHdQN5w+cUdf0YQYVp/C/2IlVw4TB4CD4DLECc9LyYxbrKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:28:45.097608Z"},"content_sha256":"c2d30aa0b826b20446b71c3be5c42215ebfa1fae0477a910eb1877ae00778285","schema_version":"1.0","event_id":"sha256:c2d30aa0b826b20446b71c3be5c42215ebfa1fae0477a910eb1877ae00778285"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QJR3TPG7UYQUPKCXMZL56NQQJG/bundle.json","state_url":"https://pith.science/pith/QJR3TPG7UYQUPKCXMZL56NQQJG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QJR3TPG7UYQUPKCXMZL56NQQJG/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":"2026-08-09T07:28:45Z","links":{"resolver":"https://pith.science/pith/QJR3TPG7UYQUPKCXMZL56NQQJG","bundle":"https://pith.science/pith/QJR3TPG7UYQUPKCXMZL56NQQJG/bundle.json","state":"https://pith.science/pith/QJR3TPG7UYQUPKCXMZL56NQQJG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QJR3TPG7UYQUPKCXMZL56NQQJG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QJR3TPG7UYQUPKCXMZL56NQQJG","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":"d7d5e73cb1a86903ddc3acea6a2bf69d5ba1297e916e8bf55af67dbd3c52cbc6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T16:59:20Z","title_canon_sha256":"ae27efc46f075999b9ab6f0b034dcac10cb40052250892e91d6dc6d2e9b10ff3"},"schema_version":"1.0","source":{"id":"2311.06612","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06612","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06612v1","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06612","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"QJR3TPG7UYQU","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"QJR3TPG7UYQUPKCX","created_at":"2026-07-05T07:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"QJR3TPG7","created_at":"2026-07-05T07:11:42Z"}],"graph_snapshots":[{"event_id":"sha256:c2d30aa0b826b20446b71c3be5c42215ebfa1fae0477a910eb1877ae00778285","target":"graph","created_at":"2026-07-05T07:11:42Z","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/2311.06612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate visual perception tasks remains a challenge. In this paper, we present a novel end-to-end framework named PerceptionGPT, which efficiently and effectively equips the VLLMs with visual perception abilities by leveraging the representation power of LLMs' token embedding. Our proposed method treats the token embedding of the LLM as the carrier of spatial informatio","authors_text":"Jiahui Gao, Jipeng Zhang, Lewei Yao, Renjie Pi, Tong Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T16:59:20Z","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06612","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":"sha256:532ce54ba04dcdd4b980d3d5e9b3aa681e6a790cb434d1a173ab51c20bee8a90","target":"record","created_at":"2026-07-05T07:11:42Z","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":"d7d5e73cb1a86903ddc3acea6a2bf69d5ba1297e916e8bf55af67dbd3c52cbc6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T16:59:20Z","title_canon_sha256":"ae27efc46f075999b9ab6f0b034dcac10cb40052250892e91d6dc6d2e9b10ff3"},"schema_version":"1.0","source":{"id":"2311.06612","kind":"arxiv","version":1}},"canonical_sha256":"8263b9bcdfa62147a8576657df3610498b99ce3aec500f10e0a247d77b7c5d30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8263b9bcdfa62147a8576657df3610498b99ce3aec500f10e0a247d77b7c5d30","first_computed_at":"2026-07-05T07:11:42.815945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:42.815945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RQ8/GwiPLzUWP8o4QjGGgDaek21MKCK6wYTDe9HMToWY4TZBwM8rUaybX4WHBRS6kNhfQbJz0H0pvsQdlIOxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:42.816481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06612","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:532ce54ba04dcdd4b980d3d5e9b3aa681e6a790cb434d1a173ab51c20bee8a90","sha256:c2d30aa0b826b20446b71c3be5c42215ebfa1fae0477a910eb1877ae00778285"],"state_sha256":"3833b8872df12c8cf31c59e17edbb74abff84a7269381b1dd17d5c97c062ba82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vWcUBMJ7XfXJOO+zECuW66LnxjOYjCnvCIBKLssFG7GQuqeArfIpscUO0Pb2YEuRovPBR1eJFYT/ovERwiZRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:28:45.103528Z","bundle_sha256":"f969d4e8f7bf28873e73fd0ad2086e5cea87fc7f21912610656ce32577f7d78d"}}