{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JB4KW7537FGYBP63AUOVZ4DJJH","short_pith_number":"pith:JB4KW753","canonical_record":{"source":{"id":"2312.02949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T18:29:31Z","cross_cats_sorted":[],"title_canon_sha256":"9c9c224b411ea42dd0b86ff9549ba7d67ee438a7608b73b542c007c7dffd494a","abstract_canon_sha256":"b133b6263dd3b38c1f7dc84e78f40db461b4bb8a95363b0a76f189d4b936e7d2"},"schema_version":"1.0"},"canonical_sha256":"4878ab7fbbf94d80bfdb051d5cf06949e03a0555c176cc45e25968012fe252d7","source":{"kind":"arxiv","id":"2312.02949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02949","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02949v1","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02949","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"JB4KW7537FGY","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"pith_short_16","alias_value":"JB4KW7537FGYBP63","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"pith_short_8","alias_value":"JB4KW753","created_at":"2026-07-05T07:20:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JB4KW7537FGYBP63AUOVZ4DJJH","target":"record","payload":{"canonical_record":{"source":{"id":"2312.02949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T18:29:31Z","cross_cats_sorted":[],"title_canon_sha256":"9c9c224b411ea42dd0b86ff9549ba7d67ee438a7608b73b542c007c7dffd494a","abstract_canon_sha256":"b133b6263dd3b38c1f7dc84e78f40db461b4bb8a95363b0a76f189d4b936e7d2"},"schema_version":"1.0"},"canonical_sha256":"4878ab7fbbf94d80bfdb051d5cf06949e03a0555c176cc45e25968012fe252d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:45.081090Z","signature_b64":"AFblEzn3ma1HWPNh2LvL+Ngbv0Gigrc3nia+pxBGtimLFGdsgS9pyHDEgVjHpmdOpY5Toxz4B1qEBy6BPNeJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4878ab7fbbf94d80bfdb051d5cf06949e03a0555c176cc45e25968012fe252d7","last_reissued_at":"2026-07-05T07:20:45.080474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:45.080474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.02949","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":"2026-07-05T07:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27D6CtCdUF+2wTPwNmx2fe1OYF1Wlo0D4uXx/LZGxBVkRL8ZTd14yROuXDZFcN9h574sr6x4p/9PbD6Lwf7CAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:47:55.967518Z"},"content_sha256":"8b2a2da943d18ea09695c31129436c1c4549ec16e6ad26cb6bb4767e8b9b0ac8","schema_version":"1.0","event_id":"sha256:8b2a2da943d18ea09695c31129436c1c4549ec16e6ad26cb6bb4767e8b9b0ac8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JB4KW7537FGYBP63AUOVZ4DJJH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Feng Li, Hao Zhang, Hongyang Li, Jianfeng Gao, Jianwei Yang, Lei Zhang, Shijia Huang, Shilong Liu, Tianhe Ren, Xueyan Zou","submitted_at":"2023-12-05T18:29:31Z","abstract_excerpt":"With the recent significant advancements in large multi-modal models (LMMs), the importance of their grounding capability in visual chat is increasingly recognized. Despite recent efforts to enable LMMs to support grounding, their capabilities for grounding and chat are usually separate, and their chat performance drops dramatically when asked to ground. The problem is the lack of a dataset for grounded visual chat (GVC). Existing grounding datasets only contain short captions. To address this issue, we have created GVC data that allows for the combination of grounding and chat capabilities. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02949","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/2312.02949/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":"2026-07-05T07:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dCivJb33AGxS/zCsnHiqkN+v2qHzxOhjet0ar/w9UmUKYYYR3/l/Nu5bfEZOq/sRtHS3hU9CkUATh4J/PkFZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:47:55.968466Z"},"content_sha256":"1737d5b8f13675affa9a47f5a577a9842c76f9413f260c4817c74cff46b1124e","schema_version":"1.0","event_id":"sha256:1737d5b8f13675affa9a47f5a577a9842c76f9413f260c4817c74cff46b1124e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JB4KW7537FGYBP63AUOVZ4DJJH/bundle.json","state_url":"https://pith.science/pith/JB4KW7537FGYBP63AUOVZ4DJJH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JB4KW7537FGYBP63AUOVZ4DJJH/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":"2026-08-05T01:47:55Z","links":{"resolver":"https://pith.science/pith/JB4KW7537FGYBP63AUOVZ4DJJH","bundle":"https://pith.science/pith/JB4KW7537FGYBP63AUOVZ4DJJH/bundle.json","state":"https://pith.science/pith/JB4KW7537FGYBP63AUOVZ4DJJH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JB4KW7537FGYBP63AUOVZ4DJJH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JB4KW7537FGYBP63AUOVZ4DJJH","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":"b133b6263dd3b38c1f7dc84e78f40db461b4bb8a95363b0a76f189d4b936e7d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T18:29:31Z","title_canon_sha256":"9c9c224b411ea42dd0b86ff9549ba7d67ee438a7608b73b542c007c7dffd494a"},"schema_version":"1.0","source":{"id":"2312.02949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02949","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02949v1","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02949","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"JB4KW7537FGY","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"pith_short_16","alias_value":"JB4KW7537FGYBP63","created_at":"2026-07-05T07:20:45Z"},{"alias_kind":"pith_short_8","alias_value":"JB4KW753","created_at":"2026-07-05T07:20:45Z"}],"graph_snapshots":[{"event_id":"sha256:1737d5b8f13675affa9a47f5a577a9842c76f9413f260c4817c74cff46b1124e","target":"graph","created_at":"2026-07-05T07:20:45Z","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/2312.02949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the recent significant advancements in large multi-modal models (LMMs), the importance of their grounding capability in visual chat is increasingly recognized. Despite recent efforts to enable LMMs to support grounding, their capabilities for grounding and chat are usually separate, and their chat performance drops dramatically when asked to ground. The problem is the lack of a dataset for grounded visual chat (GVC). Existing grounding datasets only contain short captions. To address this issue, we have created GVC data that allows for the combination of grounding and chat capabilities. T","authors_text":"Chunyuan Li, Feng Li, Hao Zhang, Hongyang Li, Jianfeng Gao, Jianwei Yang, Lei Zhang, Shijia Huang, Shilong Liu, Tianhe Ren, Xueyan Zou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T18:29:31Z","title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02949","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":"sha256:8b2a2da943d18ea09695c31129436c1c4549ec16e6ad26cb6bb4767e8b9b0ac8","target":"record","created_at":"2026-07-05T07:20:45Z","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":"b133b6263dd3b38c1f7dc84e78f40db461b4bb8a95363b0a76f189d4b936e7d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T18:29:31Z","title_canon_sha256":"9c9c224b411ea42dd0b86ff9549ba7d67ee438a7608b73b542c007c7dffd494a"},"schema_version":"1.0","source":{"id":"2312.02949","kind":"arxiv","version":1}},"canonical_sha256":"4878ab7fbbf94d80bfdb051d5cf06949e03a0555c176cc45e25968012fe252d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4878ab7fbbf94d80bfdb051d5cf06949e03a0555c176cc45e25968012fe252d7","first_computed_at":"2026-07-05T07:20:45.080474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:45.080474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AFblEzn3ma1HWPNh2LvL+Ngbv0Gigrc3nia+pxBGtimLFGdsgS9pyHDEgVjHpmdOpY5Toxz4B1qEBy6BPNeJDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:45.081090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b2a2da943d18ea09695c31129436c1c4549ec16e6ad26cb6bb4767e8b9b0ac8","sha256:1737d5b8f13675affa9a47f5a577a9842c76f9413f260c4817c74cff46b1124e"],"state_sha256":"c3241ff48a5bfcc5bd8a70268ac4404f7d355f2cfe631f357cfadc28ee107896"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D11RpGXBSon7UW2pcz/eKRjV3h+M+iKiOONlU5Z5+b9rFmfxq5b0CH3JFkKgYD3BfC7O/qzfPPOZfMW36j2zDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:47:55.973721Z","bundle_sha256":"1d3653efb99a496fc7e706a2ad3e857831f7d277fdf8234ed61f185da37ec638"}}