{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RPHCOL72H4LTFFVOKR6PIP5WV6","short_pith_number":"pith:RPHCOL72","canonical_record":{"source":{"id":"2404.06510","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"7f74bc3451ab03b9455ca2a7bd94593a7c3520ca5dcb24dfd53c7474e54b9ce6","abstract_canon_sha256":"1a4fdf00a6c4959c911689d4e9a119947077f8b8ef2dc05730603bc0b57741ad"},"schema_version":"1.0"},"canonical_sha256":"8bce272ffa3f173296ae547cf43fb6af901268c30f2bbb8d8c38c8ca6ee52a3d","source":{"kind":"arxiv","id":"2404.06510","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06510","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06510v2","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06510","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"pith_short_12","alias_value":"RPHCOL72H4LT","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"pith_short_16","alias_value":"RPHCOL72H4LTFFVO","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"pith_short_8","alias_value":"RPHCOL72","created_at":"2026-07-05T11:09:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RPHCOL72H4LTFFVOKR6PIP5WV6","target":"record","payload":{"canonical_record":{"source":{"id":"2404.06510","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"7f74bc3451ab03b9455ca2a7bd94593a7c3520ca5dcb24dfd53c7474e54b9ce6","abstract_canon_sha256":"1a4fdf00a6c4959c911689d4e9a119947077f8b8ef2dc05730603bc0b57741ad"},"schema_version":"1.0"},"canonical_sha256":"8bce272ffa3f173296ae547cf43fb6af901268c30f2bbb8d8c38c8ca6ee52a3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:42.300292Z","signature_b64":"6fxZX0R1+wLd0LqHAuVFu4epDJTOdCofwR4+/flofmJ7iBAHyy8yRq96kV3CRlSf0L+Ox9Rkf0fNPmrOUQMMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bce272ffa3f173296ae547cf43fb6af901268c30f2bbb8d8c38c8ca6ee52a3d","last_reissued_at":"2026-07-05T11:09:42.299706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:42.299706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.06510","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":"2026-07-05T11:09:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K0a3QYQT5Hw9BqKE5Tkyv4/Yn5AhymT7KjLRiVGlj5vRbElQm3WwnVWvYWJOssM/tzF7oKkZNTwxOIXrG0YEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:04:08.604921Z"},"content_sha256":"587df10c4b556fc56dcd1627193fd6d06ccc376bb5714cb864f5b434827503fa","schema_version":"1.0","event_id":"sha256:587df10c4b556fc56dcd1627193fd6d06ccc376bb5714cb864f5b434827503fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RPHCOL72H4LTFFVOKR6PIP5WV6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Acuna, Rafid Mahmood, Sanja Fidler, Yuan-Hong Liao","submitted_at":"2024-04-09T17:59:04Z","abstract_excerpt":"Enhancing semantic grounding abilities in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying the training recipes. In this work, we venture into an orthogonal direction and explore whether VLMs can improve their semantic grounding by \"receiving\" feedback, without requiring in-domain data, fine-tuning, or modifications to the network architectures. We systematically analyze this hypothesis using a feedback mechanism composed of a binary signal. We find that if prompted appropriately, VLMs can utilize feedback b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06510","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/2404.06510/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":"2026-07-05T11:09:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3Szo2yjuKZO6vfV06nxLkK0wlHgWUHPxJeuFjAvDobwb3h4+e/HZBwfDWTh75K4QRrk65HqcL23atyKJ42bCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:04:08.605297Z"},"content_sha256":"74872f7948241108147ee75da81c79c60d597c910b7d22d60e8395718eb83a3f","schema_version":"1.0","event_id":"sha256:74872f7948241108147ee75da81c79c60d597c910b7d22d60e8395718eb83a3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RPHCOL72H4LTFFVOKR6PIP5WV6/bundle.json","state_url":"https://pith.science/pith/RPHCOL72H4LTFFVOKR6PIP5WV6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RPHCOL72H4LTFFVOKR6PIP5WV6/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":"2026-07-09T05:04:08Z","links":{"resolver":"https://pith.science/pith/RPHCOL72H4LTFFVOKR6PIP5WV6","bundle":"https://pith.science/pith/RPHCOL72H4LTFFVOKR6PIP5WV6/bundle.json","state":"https://pith.science/pith/RPHCOL72H4LTFFVOKR6PIP5WV6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RPHCOL72H4LTFFVOKR6PIP5WV6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPHCOL72H4LTFFVOKR6PIP5WV6","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":"1a4fdf00a6c4959c911689d4e9a119947077f8b8ef2dc05730603bc0b57741ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:04Z","title_canon_sha256":"7f74bc3451ab03b9455ca2a7bd94593a7c3520ca5dcb24dfd53c7474e54b9ce6"},"schema_version":"1.0","source":{"id":"2404.06510","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06510","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06510v2","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06510","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"pith_short_12","alias_value":"RPHCOL72H4LT","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"pith_short_16","alias_value":"RPHCOL72H4LTFFVO","created_at":"2026-07-05T11:09:42Z"},{"alias_kind":"pith_short_8","alias_value":"RPHCOL72","created_at":"2026-07-05T11:09:42Z"}],"graph_snapshots":[{"event_id":"sha256:74872f7948241108147ee75da81c79c60d597c910b7d22d60e8395718eb83a3f","target":"graph","created_at":"2026-07-05T11:09:42Z","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/2404.06510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enhancing semantic grounding abilities in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying the training recipes. In this work, we venture into an orthogonal direction and explore whether VLMs can improve their semantic grounding by \"receiving\" feedback, without requiring in-domain data, fine-tuning, or modifications to the network architectures. We systematically analyze this hypothesis using a feedback mechanism composed of a binary signal. We find that if prompted appropriately, VLMs can utilize feedback b","authors_text":"David Acuna, Rafid Mahmood, Sanja Fidler, Yuan-Hong Liao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:04Z","title":"Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06510","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":"sha256:587df10c4b556fc56dcd1627193fd6d06ccc376bb5714cb864f5b434827503fa","target":"record","created_at":"2026-07-05T11:09:42Z","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":"1a4fdf00a6c4959c911689d4e9a119947077f8b8ef2dc05730603bc0b57741ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:04Z","title_canon_sha256":"7f74bc3451ab03b9455ca2a7bd94593a7c3520ca5dcb24dfd53c7474e54b9ce6"},"schema_version":"1.0","source":{"id":"2404.06510","kind":"arxiv","version":2}},"canonical_sha256":"8bce272ffa3f173296ae547cf43fb6af901268c30f2bbb8d8c38c8ca6ee52a3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bce272ffa3f173296ae547cf43fb6af901268c30f2bbb8d8c38c8ca6ee52a3d","first_computed_at":"2026-07-05T11:09:42.299706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:42.299706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6fxZX0R1+wLd0LqHAuVFu4epDJTOdCofwR4+/flofmJ7iBAHyy8yRq96kV3CRlSf0L+Ox9Rkf0fNPmrOUQMMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:42.300292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06510","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:587df10c4b556fc56dcd1627193fd6d06ccc376bb5714cb864f5b434827503fa","sha256:74872f7948241108147ee75da81c79c60d597c910b7d22d60e8395718eb83a3f"],"state_sha256":"04ed70832e33e21eaa80d5c4e0e53983769b424f1d916fb2c8f79bb6e0b36e45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HfW3GQF0/WJ0lF3pRYdBkLS+EIaF28nAQAQ/j/chUd0D1mE/6hrPemCtq6UPn/W1fOHH9wj3tFwMwWTXa5fLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:04:08.607296Z","bundle_sha256":"5b39f65c2898c8ebd1f5bdb252e472fd3851d5d774b6c2cd68f6015922205e52"}}