{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7WUEXR5AFISRDJUL6EP5NCZR46","short_pith_number":"pith:7WUEXR5A","canonical_record":{"source":{"id":"2403.10228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T11:58:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e67022b3d6eddc34c32baeb01fe17bdd2b18495a9854f83f838dc9ceb670c641","abstract_canon_sha256":"0665b8db195606a38e605c2ded51e85de94e1d892d9909407183d0c0e3833b76"},"schema_version":"1.0"},"canonical_sha256":"fda84bc7a02a2511a68bf11fd68b31e7b507e561ee226af2df634ebfad9c12a9","source":{"kind":"arxiv","id":"2403.10228","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10228","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10228v1","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10228","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"pith_short_12","alias_value":"7WUEXR5AFISR","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"pith_short_16","alias_value":"7WUEXR5AFISRDJUL","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"pith_short_8","alias_value":"7WUEXR5A","created_at":"2026-07-05T07:56:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7WUEXR5AFISRDJUL6EP5NCZR46","target":"record","payload":{"canonical_record":{"source":{"id":"2403.10228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T11:58:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e67022b3d6eddc34c32baeb01fe17bdd2b18495a9854f83f838dc9ceb670c641","abstract_canon_sha256":"0665b8db195606a38e605c2ded51e85de94e1d892d9909407183d0c0e3833b76"},"schema_version":"1.0"},"canonical_sha256":"fda84bc7a02a2511a68bf11fd68b31e7b507e561ee226af2df634ebfad9c12a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:32.045111Z","signature_b64":"gszb7y6SvEP8W3sLnpkuIPZBm8A5whh6UX/pyadFt5sdmPmhNvyRhQ89NxQpPXziB2UCHJvAU3577HkEjPmJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fda84bc7a02a2511a68bf11fd68b31e7b507e561ee226af2df634ebfad9c12a9","last_reissued_at":"2026-07-05T07:56:32.044602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:32.044602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.10228","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":"2026-07-05T07:56:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQ6WXaGG4fEPeMaT2E3wtimoGh4A6EqQCX4pcQ90TAmi+zJihee/MwOrxLm+zNigPjMnqLALDZj1pw1Ne62LAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:02:48.118771Z"},"content_sha256":"aa9d9ddb61b1525fbf5c4d61eb490f3292509e94c9efb5d03db257bcac19b8f7","schema_version":"1.0","event_id":"sha256:aa9d9ddb61b1525fbf5c4d61eb490f3292509e94c9efb5d03db257bcac19b8f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7WUEXR5AFISRDJUL6EP5NCZR46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Jianxin Liang, Qun Liu, Xiaojun Meng, Yueqian Wang, Yuxuan Wang","submitted_at":"2024-03-15T11:58:18Z","abstract_excerpt":"Video-text Large Language Models (video-text LLMs) have shown remarkable performance in answering questions and holding conversations on simple videos. However, they perform almost the same as random on grounding text queries in long and complicated videos, having little ability to understand and reason about temporal information, which is the most fundamental difference between videos and images. In this paper, we propose HawkEye, one of the first video-text LLMs that can perform temporal video grounding in a fully text-to-text manner. To collect training data that is applicable for temporal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10228","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/2403.10228/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":"2026-07-05T07:56:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cD311k9cy13wwC6QYdDyULgjDuvpJ6lbBBnfqZu2Ig1rViiqRecynouItqkBGkPys7X8AM2viwpIxUC215aaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:02:48.119168Z"},"content_sha256":"bc7156a95aec9bfe8e3c427af9629a5e58a8c3cbcb11334a98ba83741dff3c95","schema_version":"1.0","event_id":"sha256:bc7156a95aec9bfe8e3c427af9629a5e58a8c3cbcb11334a98ba83741dff3c95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WUEXR5AFISRDJUL6EP5NCZR46/bundle.json","state_url":"https://pith.science/pith/7WUEXR5AFISRDJUL6EP5NCZR46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WUEXR5AFISRDJUL6EP5NCZR46/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":"2026-08-04T10:02:48Z","links":{"resolver":"https://pith.science/pith/7WUEXR5AFISRDJUL6EP5NCZR46","bundle":"https://pith.science/pith/7WUEXR5AFISRDJUL6EP5NCZR46/bundle.json","state":"https://pith.science/pith/7WUEXR5AFISRDJUL6EP5NCZR46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WUEXR5AFISRDJUL6EP5NCZR46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7WUEXR5AFISRDJUL6EP5NCZR46","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":"0665b8db195606a38e605c2ded51e85de94e1d892d9909407183d0c0e3833b76","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T11:58:18Z","title_canon_sha256":"e67022b3d6eddc34c32baeb01fe17bdd2b18495a9854f83f838dc9ceb670c641"},"schema_version":"1.0","source":{"id":"2403.10228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10228","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10228v1","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10228","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"pith_short_12","alias_value":"7WUEXR5AFISR","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"pith_short_16","alias_value":"7WUEXR5AFISRDJUL","created_at":"2026-07-05T07:56:32Z"},{"alias_kind":"pith_short_8","alias_value":"7WUEXR5A","created_at":"2026-07-05T07:56:32Z"}],"graph_snapshots":[{"event_id":"sha256:bc7156a95aec9bfe8e3c427af9629a5e58a8c3cbcb11334a98ba83741dff3c95","target":"graph","created_at":"2026-07-05T07:56:32Z","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/2403.10228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-text Large Language Models (video-text LLMs) have shown remarkable performance in answering questions and holding conversations on simple videos. However, they perform almost the same as random on grounding text queries in long and complicated videos, having little ability to understand and reason about temporal information, which is the most fundamental difference between videos and images. In this paper, we propose HawkEye, one of the first video-text LLMs that can perform temporal video grounding in a fully text-to-text manner. To collect training data that is applicable for temporal ","authors_text":"Dongyan Zhao, Jianxin Liang, Qun Liu, Xiaojun Meng, Yueqian Wang, Yuxuan Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T11:58:18Z","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10228","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:aa9d9ddb61b1525fbf5c4d61eb490f3292509e94c9efb5d03db257bcac19b8f7","target":"record","created_at":"2026-07-05T07:56:32Z","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":"0665b8db195606a38e605c2ded51e85de94e1d892d9909407183d0c0e3833b76","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T11:58:18Z","title_canon_sha256":"e67022b3d6eddc34c32baeb01fe17bdd2b18495a9854f83f838dc9ceb670c641"},"schema_version":"1.0","source":{"id":"2403.10228","kind":"arxiv","version":1}},"canonical_sha256":"fda84bc7a02a2511a68bf11fd68b31e7b507e561ee226af2df634ebfad9c12a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fda84bc7a02a2511a68bf11fd68b31e7b507e561ee226af2df634ebfad9c12a9","first_computed_at":"2026-07-05T07:56:32.044602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:32.044602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gszb7y6SvEP8W3sLnpkuIPZBm8A5whh6UX/pyadFt5sdmPmhNvyRhQ89NxQpPXziB2UCHJvAU3577HkEjPmJDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:32.045111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa9d9ddb61b1525fbf5c4d61eb490f3292509e94c9efb5d03db257bcac19b8f7","sha256:bc7156a95aec9bfe8e3c427af9629a5e58a8c3cbcb11334a98ba83741dff3c95"],"state_sha256":"82f5768c52261dbac5bfb60c4b461a1ee40af34a03fba581b271d68de3393f0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XwwfgvxGV0Fx5zH+5Zan1vpO/qfb7qbBymePMnVD1XVyR5vT8yGJhASOXyTpTCPMUH1FcTfYkkZj1M5ZWFkVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:02:48.121824Z","bundle_sha256":"74d9df7f2fae64c42358170cf06141fb1614257f1dca0975970b56ae0af5e246"}}