{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N45XDU3HDO6YBFTCJQLH73OZJZ","short_pith_number":"pith:N45XDU3H","canonical_record":{"source":{"id":"2410.12813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-01T08:27:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7ff102d09ae28ad6ea53f76e1a0cf46fa0c6c9fda309060f03328ef3d3b9f484","abstract_canon_sha256":"c9cb0d7b7eee4b516d0100025c9abbd25164669b5a1f74796857a65e18b7c89c"},"schema_version":"1.0"},"canonical_sha256":"6f3b71d3671bbd8096624c167fedd94e65ca9a41a0256bcba0c69ea512a5b349","source":{"kind":"arxiv","id":"2410.12813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12813","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12813v1","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12813","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"N45XDU3HDO6Y","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_16","alias_value":"N45XDU3HDO6YBFTC","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_8","alias_value":"N45XDU3H","created_at":"2026-07-05T09:21:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N45XDU3HDO6YBFTCJQLH73OZJZ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-01T08:27:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7ff102d09ae28ad6ea53f76e1a0cf46fa0c6c9fda309060f03328ef3d3b9f484","abstract_canon_sha256":"c9cb0d7b7eee4b516d0100025c9abbd25164669b5a1f74796857a65e18b7c89c"},"schema_version":"1.0"},"canonical_sha256":"6f3b71d3671bbd8096624c167fedd94e65ca9a41a0256bcba0c69ea512a5b349","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:51.312544Z","signature_b64":"0zPo/reZZSs0oHQ6Kh255/y/sGozXNJ/4tgjPJIlybAmmt67pgmLoSyLNjzJOUPV1b68JWGtGRO0SblQ6sAKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f3b71d3671bbd8096624c167fedd94e65ca9a41a0256bcba0c69ea512a5b349","last_reissued_at":"2026-07-05T09:21:51.312137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:51.312137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12813","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":"2026-07-05T09:21:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n49IiM+niHRtCuGKKuKjeWezoASJzd9i1lBD+ygmHy+KNeH3Nr258L9nxSIF0P9UmxnD81P5HCYEyKeMr7PXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:45:24.754892Z"},"content_sha256":"b165331a9115331249798bca77550fa19e45b532d2fcf012528da61ec12ee72b","schema_version":"1.0","event_id":"sha256:b165331a9115331249798bca77550fa19e45b532d2fcf012528da61ec12ee72b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N45XDU3HDO6YBFTCJQLH73OZJZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Alicia Li, Mengxue Qu, Wu Liu, Xiaodong Chen, Yao Zhao","submitted_at":"2024-10-01T08:27:56Z","abstract_excerpt":"Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on supervised learning and extensive annotated data, which is labor-intensive and prone to human biases. To address these challenges, we present ChatVTG, a novel approach that utilizes Video Dialogue Large Language Models (LLMs) for zero-shot video temporal grounding. Our ChatVTG leverages Video Dialogue LLMs to generate multi-granularity segment captions and matches these captions with the given query for coarse tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12813","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/2410.12813/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":"2026-07-05T09:21:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/uazvtCJpYOH0ySrogjGeH2XtZIJNTJIuvjfmg7xztruqaCLPw2MA3yMFhonJL/PC3IxRMQSHmR4yxT9ykdeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:45:24.755416Z"},"content_sha256":"ff0dfb86dd5104293ef7453791e717d10a9baaeee8bc93348a451ee266578793","schema_version":"1.0","event_id":"sha256:ff0dfb86dd5104293ef7453791e717d10a9baaeee8bc93348a451ee266578793"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N45XDU3HDO6YBFTCJQLH73OZJZ/bundle.json","state_url":"https://pith.science/pith/N45XDU3HDO6YBFTCJQLH73OZJZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N45XDU3HDO6YBFTCJQLH73OZJZ/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":"2026-08-11T03:45:24Z","links":{"resolver":"https://pith.science/pith/N45XDU3HDO6YBFTCJQLH73OZJZ","bundle":"https://pith.science/pith/N45XDU3HDO6YBFTCJQLH73OZJZ/bundle.json","state":"https://pith.science/pith/N45XDU3HDO6YBFTCJQLH73OZJZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N45XDU3HDO6YBFTCJQLH73OZJZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N45XDU3HDO6YBFTCJQLH73OZJZ","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":"c9cb0d7b7eee4b516d0100025c9abbd25164669b5a1f74796857a65e18b7c89c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-01T08:27:56Z","title_canon_sha256":"7ff102d09ae28ad6ea53f76e1a0cf46fa0c6c9fda309060f03328ef3d3b9f484"},"schema_version":"1.0","source":{"id":"2410.12813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12813","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12813v1","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12813","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"N45XDU3HDO6Y","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_16","alias_value":"N45XDU3HDO6YBFTC","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_8","alias_value":"N45XDU3H","created_at":"2026-07-05T09:21:51Z"}],"graph_snapshots":[{"event_id":"sha256:ff0dfb86dd5104293ef7453791e717d10a9baaeee8bc93348a451ee266578793","target":"graph","created_at":"2026-07-05T09:21:51Z","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/2410.12813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on supervised learning and extensive annotated data, which is labor-intensive and prone to human biases. To address these challenges, we present ChatVTG, a novel approach that utilizes Video Dialogue Large Language Models (LLMs) for zero-shot video temporal grounding. Our ChatVTG leverages Video Dialogue LLMs to generate multi-granularity segment captions and matches these captions with the given query for coarse tempor","authors_text":"Alicia Li, Mengxue Qu, Wu Liu, Xiaodong Chen, Yao Zhao","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-01T08:27:56Z","title":"ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12813","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:b165331a9115331249798bca77550fa19e45b532d2fcf012528da61ec12ee72b","target":"record","created_at":"2026-07-05T09:21:51Z","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":"c9cb0d7b7eee4b516d0100025c9abbd25164669b5a1f74796857a65e18b7c89c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-01T08:27:56Z","title_canon_sha256":"7ff102d09ae28ad6ea53f76e1a0cf46fa0c6c9fda309060f03328ef3d3b9f484"},"schema_version":"1.0","source":{"id":"2410.12813","kind":"arxiv","version":1}},"canonical_sha256":"6f3b71d3671bbd8096624c167fedd94e65ca9a41a0256bcba0c69ea512a5b349","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f3b71d3671bbd8096624c167fedd94e65ca9a41a0256bcba0c69ea512a5b349","first_computed_at":"2026-07-05T09:21:51.312137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:51.312137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0zPo/reZZSs0oHQ6Kh255/y/sGozXNJ/4tgjPJIlybAmmt67pgmLoSyLNjzJOUPV1b68JWGtGRO0SblQ6sAKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:51.312544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b165331a9115331249798bca77550fa19e45b532d2fcf012528da61ec12ee72b","sha256:ff0dfb86dd5104293ef7453791e717d10a9baaeee8bc93348a451ee266578793"],"state_sha256":"cf53a0aa61cc6fcaa9c9a6bd6112bd0600aac5a32d02cd6f3146963e71bf2cfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DfXVU4urKZMtK4iaXM0abJKio1GXCuLZIQk2qcqLJD3Ujxe3GZnU5PeqdpwzSVjCPUGbPiK3g58w62jY+uJ1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:45:24.759739Z","bundle_sha256":"d4feff4fa59565cbc851ac45262035244b62fcfdb10898e498d9f9cf7e8a5690"}}