{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Z3ZF2YY76ZNNNV6BT25EQ3BCNE","short_pith_number":"pith:Z3ZF2YY7","canonical_record":{"source":{"id":"2212.09737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T18:55:43Z","cross_cats_sorted":[],"title_canon_sha256":"f38f99b5a0d5ee13705702ab66054f8fd41f6a08217f8b1dc7483e14c648fe64","abstract_canon_sha256":"f2a3fce1074ab64d57aa791fd6c89d482b396b6a80611b8bb3b15ee7e1526767"},"schema_version":"1.0"},"canonical_sha256":"cef25d631ff65ad6d7c19eba486c2269032be9cdfd7bea69dc00547c72097c1a","source":{"kind":"arxiv","id":"2212.09737","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09737","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09737v2","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09737","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"Z3ZF2YY76ZNN","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"Z3ZF2YY76ZNNNV6B","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"Z3ZF2YY7","created_at":"2026-07-05T06:18:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Z3ZF2YY76ZNNNV6BT25EQ3BCNE","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T18:55:43Z","cross_cats_sorted":[],"title_canon_sha256":"f38f99b5a0d5ee13705702ab66054f8fd41f6a08217f8b1dc7483e14c648fe64","abstract_canon_sha256":"f2a3fce1074ab64d57aa791fd6c89d482b396b6a80611b8bb3b15ee7e1526767"},"schema_version":"1.0"},"canonical_sha256":"cef25d631ff65ad6d7c19eba486c2269032be9cdfd7bea69dc00547c72097c1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:19.368331Z","signature_b64":"fsRMwqNvBPHXzCvSYxgzwDZjn118/S8jMrzmtWWjaY4vXV84Hvw8cX2C0JbacGtn/TQ5BzEfLUkcuMMu0tbOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef25d631ff65ad6d7c19eba486c2269032be9cdfd7bea69dc00547c72097c1a","last_reissued_at":"2026-07-05T06:18:19.367868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:19.367868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09737","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":"2026-07-05T06:18:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHZrqwVRL9sjh+DsrJ0cjZx/NUDILK6Rp5X31MKYkJSAHhEhMKBrZy9hagJQSzmnEWxhrAdGtFovwSHzvKAQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:25:19.886111Z"},"content_sha256":"254ca38ece33bbe3947dd4a962929ac323bbca3b6c03287416baf8c3a644ae61","schema_version":"1.0","event_id":"sha256:254ca38ece33bbe3947dd4a962929ac323bbca3b6c03287416baf8c3a644ae61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Z3ZF2YY76ZNNNV6BT25EQ3BCNE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Position-guided Text Prompt for Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Mike Zheng Shou, Pan Zhou, Shuicheng Yan","submitted_at":"2022-12-19T18:55:43Z","abstract_excerpt":"Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into $N\\times N$ blocks, and identifies the objects in each block thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09737","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/2212.09737/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":"2026-07-05T06:18:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"voONnWQXFNxDxHCUGeBY+egN0A36dnvXLHOICrF7JeFRd6mZVOvT63mCTl4+StWn8AZxLhWhuGnS254bEfnADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:25:19.886611Z"},"content_sha256":"484a3e2261402ccbe8d86868ad404c9dd00157c1621ca87a4867b0df62c857c3","schema_version":"1.0","event_id":"sha256:484a3e2261402ccbe8d86868ad404c9dd00157c1621ca87a4867b0df62c857c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/bundle.json","state_url":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/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":"2026-08-09T13:25:19Z","links":{"resolver":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE","bundle":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/bundle.json","state":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z3ZF2YY76ZNNNV6BT25EQ3BCNE","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":"f2a3fce1074ab64d57aa791fd6c89d482b396b6a80611b8bb3b15ee7e1526767","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T18:55:43Z","title_canon_sha256":"f38f99b5a0d5ee13705702ab66054f8fd41f6a08217f8b1dc7483e14c648fe64"},"schema_version":"1.0","source":{"id":"2212.09737","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09737","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09737v2","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09737","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"Z3ZF2YY76ZNN","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"Z3ZF2YY76ZNNNV6B","created_at":"2026-07-05T06:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"Z3ZF2YY7","created_at":"2026-07-05T06:18:19Z"}],"graph_snapshots":[{"event_id":"sha256:484a3e2261402ccbe8d86868ad404c9dd00157c1621ca87a4867b0df62c857c3","target":"graph","created_at":"2026-07-05T06:18:19Z","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/2212.09737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into $N\\times N$ blocks, and identifies the objects in each block thr","authors_text":"Alex Jinpeng Wang, Mike Zheng Shou, Pan Zhou, Shuicheng Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T18:55:43Z","title":"Position-guided Text Prompt for Vision-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09737","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":"sha256:254ca38ece33bbe3947dd4a962929ac323bbca3b6c03287416baf8c3a644ae61","target":"record","created_at":"2026-07-05T06:18:19Z","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":"f2a3fce1074ab64d57aa791fd6c89d482b396b6a80611b8bb3b15ee7e1526767","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T18:55:43Z","title_canon_sha256":"f38f99b5a0d5ee13705702ab66054f8fd41f6a08217f8b1dc7483e14c648fe64"},"schema_version":"1.0","source":{"id":"2212.09737","kind":"arxiv","version":2}},"canonical_sha256":"cef25d631ff65ad6d7c19eba486c2269032be9cdfd7bea69dc00547c72097c1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cef25d631ff65ad6d7c19eba486c2269032be9cdfd7bea69dc00547c72097c1a","first_computed_at":"2026-07-05T06:18:19.367868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:19.367868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fsRMwqNvBPHXzCvSYxgzwDZjn118/S8jMrzmtWWjaY4vXV84Hvw8cX2C0JbacGtn/TQ5BzEfLUkcuMMu0tbOCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:19.368331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09737","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:254ca38ece33bbe3947dd4a962929ac323bbca3b6c03287416baf8c3a644ae61","sha256:484a3e2261402ccbe8d86868ad404c9dd00157c1621ca87a4867b0df62c857c3"],"state_sha256":"9f1dfa7726691ccaa82b32821697da1e94147ff045011681f87f8e00b516af7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AiZN1I6aNj0Gp6RuFAa995szeLd79UwxArdvFUypAeqbfwsPai1sp3xTBTuQIAK30na2ozV6ErPMYaC5+nNTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:25:19.891795Z","bundle_sha256":"517c27a8e35a6774164372b576a861eb1ecc37f0f14393e5c3ec86ecfba38528"}}