{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A7Q2SZIYEFLNKBP45OXU67WTNT","short_pith_number":"pith:A7Q2SZIY","canonical_record":{"source":{"id":"2403.02325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:55:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"02115b203ccaf19f135fee9b419c6e44565da40d201791997b24613327d452a9","abstract_canon_sha256":"4d5979f236e00de0fd0306baa657664c95436629befe6167e6a85ea12728aa90"},"schema_version":"1.0"},"canonical_sha256":"07e1a965182156d505fcebaf4f7ed36cd392c6f838d300a54de9bc1bef38ca83","source":{"kind":"arxiv","id":"2403.02325","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02325","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02325v1","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02325","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_12","alias_value":"A7Q2SZIYEFLN","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_16","alias_value":"A7Q2SZIYEFLNKBP4","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_8","alias_value":"A7Q2SZIY","created_at":"2026-07-05T07:51:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A7Q2SZIYEFLNKBP45OXU67WTNT","target":"record","payload":{"canonical_record":{"source":{"id":"2403.02325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:55:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"02115b203ccaf19f135fee9b419c6e44565da40d201791997b24613327d452a9","abstract_canon_sha256":"4d5979f236e00de0fd0306baa657664c95436629befe6167e6a85ea12728aa90"},"schema_version":"1.0"},"canonical_sha256":"07e1a965182156d505fcebaf4f7ed36cd392c6f838d300a54de9bc1bef38ca83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:59.428142Z","signature_b64":"4rjl/mjKE1AOlLZl8eH2DsjzdZUb13w5QPPtXkDtLK7hEPJNY4Sw90I/ONDWbgH/mzjDR8a9yJoFmgDRr/GuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07e1a965182156d505fcebaf4f7ed36cd392c6f838d300a54de9bc1bef38ca83","last_reissued_at":"2026-07-05T07:51:59.427700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:59.427700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.02325","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":"2026-07-05T07:51:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eeQC98CF/VQIVnAY/tCzKbDBc8OykVXgzoJAgpNR0+yvXbvZq95YqJs3tSdccpQ7KPcy2b961StFVRvXUfO4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:09:39.956073Z"},"content_sha256":"469df5195ffcd69a211fe37a8dcb723a6dc3567446107b4841716f75793403b0","schema_version":"1.0","event_id":"sha256:469df5195ffcd69a211fe37a8dcb723a6dc3567446107b4841716f75793403b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A7Q2SZIYEFLNKBP45OXU67WTNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Wan, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal","submitted_at":"2024-03-04T18:55:30Z","abstract_excerpt":"Highlighting particularly relevant regions of an image can improve the performance of vision-language models (VLMs) on various vision-language (VL) tasks by guiding the model to attend more closely to these regions of interest. For example, VLMs can be given a \"visual prompt\", where visual markers such as bounding boxes delineate key image regions. However, current VLMs that can incorporate visual guidance are either proprietary and expensive or require costly training on curated data that includes visual prompts. We introduce Contrastive Region Guidance (CRG), a training-free guidance method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02325","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/2403.02325/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":"2026-07-05T07:51:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4DF1FIwzzJEOUoQpp8nkYuRUaBmOdrcizycY9SNxXHBxb2mjhwX4nNzVh0dOEXh/+cWQsumvKu+/0CXRPBAoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:09:39.956581Z"},"content_sha256":"e863fda6317d856f7e98c7bf872b5735396686d19f79cb39dd0ff994cd269a46","schema_version":"1.0","event_id":"sha256:e863fda6317d856f7e98c7bf872b5735396686d19f79cb39dd0ff994cd269a46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A7Q2SZIYEFLNKBP45OXU67WTNT/bundle.json","state_url":"https://pith.science/pith/A7Q2SZIYEFLNKBP45OXU67WTNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A7Q2SZIYEFLNKBP45OXU67WTNT/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":"2026-08-06T08:09:39Z","links":{"resolver":"https://pith.science/pith/A7Q2SZIYEFLNKBP45OXU67WTNT","bundle":"https://pith.science/pith/A7Q2SZIYEFLNKBP45OXU67WTNT/bundle.json","state":"https://pith.science/pith/A7Q2SZIYEFLNKBP45OXU67WTNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A7Q2SZIYEFLNKBP45OXU67WTNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A7Q2SZIYEFLNKBP45OXU67WTNT","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":"4d5979f236e00de0fd0306baa657664c95436629befe6167e6a85ea12728aa90","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:55:30Z","title_canon_sha256":"02115b203ccaf19f135fee9b419c6e44565da40d201791997b24613327d452a9"},"schema_version":"1.0","source":{"id":"2403.02325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02325","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02325v1","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02325","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_12","alias_value":"A7Q2SZIYEFLN","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_16","alias_value":"A7Q2SZIYEFLNKBP4","created_at":"2026-07-05T07:51:59Z"},{"alias_kind":"pith_short_8","alias_value":"A7Q2SZIY","created_at":"2026-07-05T07:51:59Z"}],"graph_snapshots":[{"event_id":"sha256:e863fda6317d856f7e98c7bf872b5735396686d19f79cb39dd0ff994cd269a46","target":"graph","created_at":"2026-07-05T07:51:59Z","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/2403.02325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Highlighting particularly relevant regions of an image can improve the performance of vision-language models (VLMs) on various vision-language (VL) tasks by guiding the model to attend more closely to these regions of interest. For example, VLMs can be given a \"visual prompt\", where visual markers such as bounding boxes delineate key image regions. However, current VLMs that can incorporate visual guidance are either proprietary and expensive or require costly training on curated data that includes visual prompts. We introduce Contrastive Region Guidance (CRG), a training-free guidance method ","authors_text":"David Wan, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:55:30Z","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02325","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":"sha256:469df5195ffcd69a211fe37a8dcb723a6dc3567446107b4841716f75793403b0","target":"record","created_at":"2026-07-05T07:51:59Z","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":"4d5979f236e00de0fd0306baa657664c95436629befe6167e6a85ea12728aa90","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:55:30Z","title_canon_sha256":"02115b203ccaf19f135fee9b419c6e44565da40d201791997b24613327d452a9"},"schema_version":"1.0","source":{"id":"2403.02325","kind":"arxiv","version":1}},"canonical_sha256":"07e1a965182156d505fcebaf4f7ed36cd392c6f838d300a54de9bc1bef38ca83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07e1a965182156d505fcebaf4f7ed36cd392c6f838d300a54de9bc1bef38ca83","first_computed_at":"2026-07-05T07:51:59.427700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:59.427700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4rjl/mjKE1AOlLZl8eH2DsjzdZUb13w5QPPtXkDtLK7hEPJNY4Sw90I/ONDWbgH/mzjDR8a9yJoFmgDRr/GuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:59.428142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.02325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:469df5195ffcd69a211fe37a8dcb723a6dc3567446107b4841716f75793403b0","sha256:e863fda6317d856f7e98c7bf872b5735396686d19f79cb39dd0ff994cd269a46"],"state_sha256":"97f809f53ee2ab4d454a178acda5306896995b7d12b11aa2c1228c5fc7c9c8aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75bhS2Ccv0qy+lCa6pZeQmEMxO2EPa70Ae9YWVG+mGPEFtQolD4xGb1EScMWDWcEoNLqcp9kT5kkhxTwe8fgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:09:39.960558Z","bundle_sha256":"71f0fe93047d827bcdcbbe531983cf783862475af1889bc0940d8549848f6550"}}