{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GKMJZZPXCLFTIUOYVVWJNK3DDB","short_pith_number":"pith:GKMJZZPX","canonical_record":{"source":{"id":"2304.14407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"e5a84f2fd7e20dc54941fd1be6a008c960b4e295820206ef983d9a811d3e5889","abstract_canon_sha256":"937636bf35f9109e288c5ec2f5fb56cdada230e77d139630e949d9b1f4c3c269"},"schema_version":"1.0"},"canonical_sha256":"32989ce5f712cb3451d8ad6c96ab6318514bfab2f932cc0dee93a9a9b8869af7","source":{"kind":"arxiv","id":"2304.14407","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14407","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14407v2","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14407","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"GKMJZZPXCLFT","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"pith_short_16","alias_value":"GKMJZZPXCLFTIUOY","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"pith_short_8","alias_value":"GKMJZZPX","created_at":"2026-07-05T06:05:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GKMJZZPXCLFTIUOYVVWJNK3DDB","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"e5a84f2fd7e20dc54941fd1be6a008c960b4e295820206ef983d9a811d3e5889","abstract_canon_sha256":"937636bf35f9109e288c5ec2f5fb56cdada230e77d139630e949d9b1f4c3c269"},"schema_version":"1.0"},"canonical_sha256":"32989ce5f712cb3451d8ad6c96ab6318514bfab2f932cc0dee93a9a9b8869af7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:36.196278Z","signature_b64":"oHOebvX7zIwhwHRT8pjPXgXIsIXEvGxdhHRaTnlpaVBQOxKxltzNfGq+MT6rKFd8uG3I+3/yURlbL5R261yFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32989ce5f712cb3451d8ad6c96ab6318514bfab2f932cc0dee93a9a9b8869af7","last_reissued_at":"2026-07-05T06:05:36.195850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:36.195850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14407","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:05:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sZv3Nhzaz7GLz6PNfKGfx7whqIJ0d6WbQryDz5a4Kjxh1T8C4ijcm457Q0XTiBWGaIqYIvzx716PazBYuTGDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:11:22.434346Z"},"content_sha256":"cc74acc39955e69f37eee11de52b3b80e1ff4e186ed0f8f48333926dcbc84023","schema_version":"1.0","event_id":"sha256:cc74acc39955e69f37eee11de52b3b80e1ff4e186ed0f8f48333926dcbc84023"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GKMJZZPXCLFTIUOYVVWJNK3DDB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Luo, Dongdong Chen, Junke Wang, Lu Yuan, Xiyang Dai, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2023-04-27T17:59:58Z","abstract_excerpt":"Existing deep video models are limited by specific tasks, fixed input-output spaces, and poor generalization capabilities, making it difficult to deploy them in real-world scenarios. In this paper, we present our vision for multimodal and versatile video understanding and propose a prototype system, \\system. Our system is built upon a tracklet-centric paradigm, which treats tracklets as the basic video unit and employs various Video Foundation Models (ViFMs) to annotate their properties e.g., appearance, motion, \\etc. All the detected tracklets are stored in a database and interact with the us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14407","kind":"arxiv","version":2},"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/2304.14407/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":"2026-07-05T06:05:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCv5nsMwZl89DWkfUsvMEfpMuim2/goQbc6XdS29uftX17YBHECVGySeRvAhnENCWuSaavONqujJBo8oGf3XBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:11:22.434880Z"},"content_sha256":"be932b636b53c5cdc140e00b3e86d48b62bc71392b29963f5c1243762d7ad792","schema_version":"1.0","event_id":"sha256:be932b636b53c5cdc140e00b3e86d48b62bc71392b29963f5c1243762d7ad792"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKMJZZPXCLFTIUOYVVWJNK3DDB/bundle.json","state_url":"https://pith.science/pith/GKMJZZPXCLFTIUOYVVWJNK3DDB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKMJZZPXCLFTIUOYVVWJNK3DDB/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":"2026-08-04T22:11:22Z","links":{"resolver":"https://pith.science/pith/GKMJZZPXCLFTIUOYVVWJNK3DDB","bundle":"https://pith.science/pith/GKMJZZPXCLFTIUOYVVWJNK3DDB/bundle.json","state":"https://pith.science/pith/GKMJZZPXCLFTIUOYVVWJNK3DDB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKMJZZPXCLFTIUOYVVWJNK3DDB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GKMJZZPXCLFTIUOYVVWJNK3DDB","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":"937636bf35f9109e288c5ec2f5fb56cdada230e77d139630e949d9b1f4c3c269","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:59:58Z","title_canon_sha256":"e5a84f2fd7e20dc54941fd1be6a008c960b4e295820206ef983d9a811d3e5889"},"schema_version":"1.0","source":{"id":"2304.14407","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14407","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14407v2","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14407","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"GKMJZZPXCLFT","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"pith_short_16","alias_value":"GKMJZZPXCLFTIUOY","created_at":"2026-07-05T06:05:36Z"},{"alias_kind":"pith_short_8","alias_value":"GKMJZZPX","created_at":"2026-07-05T06:05:36Z"}],"graph_snapshots":[{"event_id":"sha256:be932b636b53c5cdc140e00b3e86d48b62bc71392b29963f5c1243762d7ad792","target":"graph","created_at":"2026-07-05T06:05:36Z","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/2304.14407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing deep video models are limited by specific tasks, fixed input-output spaces, and poor generalization capabilities, making it difficult to deploy them in real-world scenarios. In this paper, we present our vision for multimodal and versatile video understanding and propose a prototype system, \\system. Our system is built upon a tracklet-centric paradigm, which treats tracklets as the basic video unit and employs various Video Foundation Models (ViFMs) to annotate their properties e.g., appearance, motion, \\etc. All the detected tracklets are stored in a database and interact with the us","authors_text":"Chong Luo, Dongdong Chen, Junke Wang, Lu Yuan, Xiyang Dai, Yu-Gang Jiang, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:59:58Z","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14407","kind":"arxiv","version":2},"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:cc74acc39955e69f37eee11de52b3b80e1ff4e186ed0f8f48333926dcbc84023","target":"record","created_at":"2026-07-05T06:05:36Z","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":"937636bf35f9109e288c5ec2f5fb56cdada230e77d139630e949d9b1f4c3c269","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:59:58Z","title_canon_sha256":"e5a84f2fd7e20dc54941fd1be6a008c960b4e295820206ef983d9a811d3e5889"},"schema_version":"1.0","source":{"id":"2304.14407","kind":"arxiv","version":2}},"canonical_sha256":"32989ce5f712cb3451d8ad6c96ab6318514bfab2f932cc0dee93a9a9b8869af7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32989ce5f712cb3451d8ad6c96ab6318514bfab2f932cc0dee93a9a9b8869af7","first_computed_at":"2026-07-05T06:05:36.195850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:36.195850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oHOebvX7zIwhwHRT8pjPXgXIsIXEvGxdhHRaTnlpaVBQOxKxltzNfGq+MT6rKFd8uG3I+3/yURlbL5R261yFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:36.196278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14407","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc74acc39955e69f37eee11de52b3b80e1ff4e186ed0f8f48333926dcbc84023","sha256:be932b636b53c5cdc140e00b3e86d48b62bc71392b29963f5c1243762d7ad792"],"state_sha256":"fef4f9710a9599923af8d9fe06f48678f97c0db8838f0bbe0ad57c310f954933"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DqDQCsJKm6rGIetiu2ZhnTWoLv9f1SOrqEL2tcWEY7FqQ/2NVTLo30bNvAmj01IkcGmB8ibtw+hjQ8MPhuKaDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:11:22.438455Z","bundle_sha256":"8fe62373d545872da1cbd3dd8849081776fe090074f853eba28b6be3d5403e52"}}