{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OWWPX2ROFJ3IWWCYH37HR73YGB","short_pith_number":"pith:OWWPX2RO","canonical_record":{"source":{"id":"2312.15043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T20:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"cff0ec176dbab74b6fc6611b802620327b7fbbb81ca4f951b7dd067047ff8928","abstract_canon_sha256":"b72c19987bd374d78658557c24fcd973ae8f55ea26ceecee52638e9f61f99bdd"},"schema_version":"1.0"},"canonical_sha256":"75acfbea2e2a768b58583efe78ff783052fe19b7272badf0a6bd957fead498ca","source":{"kind":"arxiv","id":"2312.15043","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15043","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15043v1","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15043","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"pith_short_12","alias_value":"OWWPX2ROFJ3I","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"OWWPX2ROFJ3IWWCY","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"OWWPX2RO","created_at":"2026-07-05T07:27:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OWWPX2ROFJ3IWWCYH37HR73YGB","target":"record","payload":{"canonical_record":{"source":{"id":"2312.15043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T20:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"cff0ec176dbab74b6fc6611b802620327b7fbbb81ca4f951b7dd067047ff8928","abstract_canon_sha256":"b72c19987bd374d78658557c24fcd973ae8f55ea26ceecee52638e9f61f99bdd"},"schema_version":"1.0"},"canonical_sha256":"75acfbea2e2a768b58583efe78ff783052fe19b7272badf0a6bd957fead498ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:30.240924Z","signature_b64":"w3w/9IQ7DKF+6ViYzBWbX31TFW3a9UvHqTYjzMeZYS5x2fcpKkZdLqkoQ7TRxMSygSMfVTJAnvVPxUqGYj+oBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75acfbea2e2a768b58583efe78ff783052fe19b7272badf0a6bd957fead498ca","last_reissued_at":"2026-07-05T07:27:30.240454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:30.240454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.15043","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":"2026-07-05T07:27:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vIYImkp2JokdwTUpvD2F1F0ApmqRfMjhJ+P6mu9deY6F9YuipI2kLRS5L93t8k7wgN/7W7WpXTasVk0JoYEmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:58:59.211866Z"},"content_sha256":"b6b740f7c010c8cf9bcc562147bf5323847e6894011441ae16a1588190ef3b74","schema_version":"1.0","event_id":"sha256:b6b740f7c010c8cf9bcc562147bf5323847e6894011441ae16a1588190ef3b74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OWWPX2ROFJ3IWWCYH37HR73YGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhan Shen, Jianwei Yin, Mingwei Zhu, Tiancheng Zhao","submitted_at":"2023-12-22T20:14:55Z","abstract_excerpt":"Visual grounding, a crucial vision-language task involving the understanding of the visual context based on the query expression, necessitates the model to capture the interactions between objects, as well as various spatial and attribute information. However, the annotation data of visual grounding task is limited due to its time-consuming and labor-intensive annotation process, resulting in the trained models being constrained from generalizing its capability to a broader domain. To address this challenge, we propose GroundVLP, a simple yet effective zero-shot method that harnesses visual gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15043","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/2312.15043/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":"2026-07-05T07:27:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f66h50oGUMi3IuBIMoMImZMHswLVBFyIDeaftIw7SMEpcgY68Cbz5l6KRdKqazHCJZqPuMjLELUihAMEJkKqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:58:59.212383Z"},"content_sha256":"59ed3cbc0765167e0517464f0e1792448d514c7c1af08b9149c7f9a2fad35a95","schema_version":"1.0","event_id":"sha256:59ed3cbc0765167e0517464f0e1792448d514c7c1af08b9149c7f9a2fad35a95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWWPX2ROFJ3IWWCYH37HR73YGB/bundle.json","state_url":"https://pith.science/pith/OWWPX2ROFJ3IWWCYH37HR73YGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWWPX2ROFJ3IWWCYH37HR73YGB/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":"2026-08-23T13:58:59Z","links":{"resolver":"https://pith.science/pith/OWWPX2ROFJ3IWWCYH37HR73YGB","bundle":"https://pith.science/pith/OWWPX2ROFJ3IWWCYH37HR73YGB/bundle.json","state":"https://pith.science/pith/OWWPX2ROFJ3IWWCYH37HR73YGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWWPX2ROFJ3IWWCYH37HR73YGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OWWPX2ROFJ3IWWCYH37HR73YGB","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":"b72c19987bd374d78658557c24fcd973ae8f55ea26ceecee52638e9f61f99bdd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T20:14:55Z","title_canon_sha256":"cff0ec176dbab74b6fc6611b802620327b7fbbb81ca4f951b7dd067047ff8928"},"schema_version":"1.0","source":{"id":"2312.15043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15043","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15043v1","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15043","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"pith_short_12","alias_value":"OWWPX2ROFJ3I","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"OWWPX2ROFJ3IWWCY","created_at":"2026-07-05T07:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"OWWPX2RO","created_at":"2026-07-05T07:27:30Z"}],"graph_snapshots":[{"event_id":"sha256:59ed3cbc0765167e0517464f0e1792448d514c7c1af08b9149c7f9a2fad35a95","target":"graph","created_at":"2026-07-05T07:27:30Z","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/2312.15043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding, a crucial vision-language task involving the understanding of the visual context based on the query expression, necessitates the model to capture the interactions between objects, as well as various spatial and attribute information. However, the annotation data of visual grounding task is limited due to its time-consuming and labor-intensive annotation process, resulting in the trained models being constrained from generalizing its capability to a broader domain. To address this challenge, we propose GroundVLP, a simple yet effective zero-shot method that harnesses visual gr","authors_text":"Haozhan Shen, Jianwei Yin, Mingwei Zhu, Tiancheng Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T20:14:55Z","title":"GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15043","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:b6b740f7c010c8cf9bcc562147bf5323847e6894011441ae16a1588190ef3b74","target":"record","created_at":"2026-07-05T07:27:30Z","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":"b72c19987bd374d78658557c24fcd973ae8f55ea26ceecee52638e9f61f99bdd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T20:14:55Z","title_canon_sha256":"cff0ec176dbab74b6fc6611b802620327b7fbbb81ca4f951b7dd067047ff8928"},"schema_version":"1.0","source":{"id":"2312.15043","kind":"arxiv","version":1}},"canonical_sha256":"75acfbea2e2a768b58583efe78ff783052fe19b7272badf0a6bd957fead498ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75acfbea2e2a768b58583efe78ff783052fe19b7272badf0a6bd957fead498ca","first_computed_at":"2026-07-05T07:27:30.240454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:30.240454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w3w/9IQ7DKF+6ViYzBWbX31TFW3a9UvHqTYjzMeZYS5x2fcpKkZdLqkoQ7TRxMSygSMfVTJAnvVPxUqGYj+oBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:30.240924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6b740f7c010c8cf9bcc562147bf5323847e6894011441ae16a1588190ef3b74","sha256:59ed3cbc0765167e0517464f0e1792448d514c7c1af08b9149c7f9a2fad35a95"],"state_sha256":"5dfdb479e4158dac36b061af8599e3ff08237f3275ad63803d3cb5b09c4c4e8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2vO2gS4xM7Nrf4Qp5UyUh4lOAx6RCNfTqEHhLy/I7Xb5JYaP60cV+xUT6rsUcPtvmgqu/rVDyf7M+JtKEDvpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T13:58:59.217189Z","bundle_sha256":"78a71ae7b4bfb01d29d2540f9356a12715147639a8d7a619ca7f27d5869bd382"}}