{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5FKOORJONT7DU4IXZH3SSE56PL","short_pith_number":"pith:5FKOORJO","canonical_record":{"source":{"id":"2401.00901","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"d0dda2143575ae2e47aa54ab5937aa8788b1b1b68c32e3b1ae88b2b69be34fd5","abstract_canon_sha256":"d50b23f3775b99ba3866213be94bbd639c6a143311d726244bc596f1ea3f8c91"},"schema_version":"1.0"},"canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","source":{"kind":"arxiv","id":"2401.00901","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00901","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00901v2","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00901","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"5FKOORJONT7D","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"5FKOORJONT7DU4IX","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"5FKOORJO","created_at":"2026-07-05T08:02:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5FKOORJONT7DU4IXZH3SSE56PL","target":"record","payload":{"canonical_record":{"source":{"id":"2401.00901","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"d0dda2143575ae2e47aa54ab5937aa8788b1b1b68c32e3b1ae88b2b69be34fd5","abstract_canon_sha256":"d50b23f3775b99ba3866213be94bbd639c6a143311d726244bc596f1ea3f8c91"},"schema_version":"1.0"},"canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:23.698551Z","signature_b64":"lUeMmHIbnxXDPK+UGQvzI69C1YASPh4z3ojG/YmutsS7mblqTbV7yzCUE8WBRJyiTXoYkRpIm3eDnAEykZ18AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","last_reissued_at":"2026-07-05T08:02:23.698054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:23.698054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.00901","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":"2026-07-05T08:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0eQHMO5PpaKU90BPzDPi+NhTgDeprmzkP7bM3tlDrVEUYA3l9JvOWOy+vCovcnI+g8kjlPjdL5xnjxb6qG7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:28:19.004407Z"},"content_sha256":"a3ac925647cc10fed794123abb2ca635c0460bde10c6ea5a44e9da6fe6691413","schema_version":"1.0","event_id":"sha256:a3ac925647cc10fed794123abb2ca635c0460bde10c6ea5a44e9da6fe6691413"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5FKOORJONT7DU4IXZH3SSE56PL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Ming-Hsuan Yang, Muzammal Naseer, Salman Khan, Syed Talal Wasim","submitted_at":"2023-12-31T13:53:37Z","abstract_excerpt":"Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary Spatio-Temporal Video Grounding task. Unlike prevalent closed-set approaches that struggle with open-vocabulary scenarios due to limited training data and predefined vocabularies, our model leverages pre-trained representations from foundational spatial grounding models. This empowers it to effectively bridge the semantic gap between natural language and diverse visual co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00901","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/2401.00901/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":"2026-07-05T08:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D5OCVTnd9ZX7rwTk3Oi15156vz+rzrwQqHQT641luCRqMjSSvgAHGVbb8y+vJe9d5UD+hqcdPeQKA0UH7GIaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:28:19.005041Z"},"content_sha256":"b704e0f91d131162c99e6b2aaf9bf8b74a035f843deb3b2dac1564596670f2c7","schema_version":"1.0","event_id":"sha256:b704e0f91d131162c99e6b2aaf9bf8b74a035f843deb3b2dac1564596670f2c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/bundle.json","state_url":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FKOORJONT7DU4IXZH3SSE56PL/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":"2026-07-07T05:28:19Z","links":{"resolver":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL","bundle":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/bundle.json","state":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FKOORJONT7DU4IXZH3SSE56PL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5FKOORJONT7DU4IXZH3SSE56PL","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":"d50b23f3775b99ba3866213be94bbd639c6a143311d726244bc596f1ea3f8c91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","title_canon_sha256":"d0dda2143575ae2e47aa54ab5937aa8788b1b1b68c32e3b1ae88b2b69be34fd5"},"schema_version":"1.0","source":{"id":"2401.00901","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00901","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00901v2","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00901","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"5FKOORJONT7D","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"5FKOORJONT7DU4IX","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"5FKOORJO","created_at":"2026-07-05T08:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:b704e0f91d131162c99e6b2aaf9bf8b74a035f843deb3b2dac1564596670f2c7","target":"graph","created_at":"2026-07-05T08:02:23Z","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/2401.00901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary Spatio-Temporal Video Grounding task. Unlike prevalent closed-set approaches that struggle with open-vocabulary scenarios due to limited training data and predefined vocabularies, our model leverages pre-trained representations from foundational spatial grounding models. This empowers it to effectively bridge the semantic gap between natural language and diverse visual co","authors_text":"Fahad Shahbaz Khan, Ming-Hsuan Yang, Muzammal Naseer, Salman Khan, Syed Talal Wasim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","title":"Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00901","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:a3ac925647cc10fed794123abb2ca635c0460bde10c6ea5a44e9da6fe6691413","target":"record","created_at":"2026-07-05T08:02:23Z","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":"d50b23f3775b99ba3866213be94bbd639c6a143311d726244bc596f1ea3f8c91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","title_canon_sha256":"d0dda2143575ae2e47aa54ab5937aa8788b1b1b68c32e3b1ae88b2b69be34fd5"},"schema_version":"1.0","source":{"id":"2401.00901","kind":"arxiv","version":2}},"canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","first_computed_at":"2026-07-05T08:02:23.698054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:23.698054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lUeMmHIbnxXDPK+UGQvzI69C1YASPh4z3ojG/YmutsS7mblqTbV7yzCUE8WBRJyiTXoYkRpIm3eDnAEykZ18AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:23.698551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00901","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3ac925647cc10fed794123abb2ca635c0460bde10c6ea5a44e9da6fe6691413","sha256:b704e0f91d131162c99e6b2aaf9bf8b74a035f843deb3b2dac1564596670f2c7"],"state_sha256":"20939fa5c13073da3815003b324a32266bb0ea4da1d7fb0c6078b088628566ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vnnxDjPEonz4VYIwQtX8SXFTYKSSiJ/ekSnQfnLDAoXq2nPw1J/1zAqsh7IPD6Eak107K3BQxteGhVDtxqpqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:28:19.008550Z","bundle_sha256":"a861f81491789593961bf641dd3f3e9a17e132ab8ff9e4f6ea0853b34118caee"}}