{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:US54GJ4YDEH7QLK3HLQQ7FB5GW","short_pith_number":"pith:US54GJ4Y","canonical_record":{"source":{"id":"2206.15462","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T17:55:12Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"fb14dfdd1a131a51df748c65431f32fe6e7d022aae3806648cb741fc32ceaf79","abstract_canon_sha256":"e1ea7d06fba37448f2d00a515202ad2bd861ce6f2b96878712179cf0a25704c9"},"schema_version":"1.0"},"canonical_sha256":"a4bbc32798190ff82d5b3ae10f943d35b94e368d730b528de494608200654756","source":{"kind":"arxiv","id":"2206.15462","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15462","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15462v4","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15462","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"pith_short_12","alias_value":"US54GJ4YDEH7","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"pith_short_16","alias_value":"US54GJ4YDEH7QLK3","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"pith_short_8","alias_value":"US54GJ4Y","created_at":"2026-07-05T07:30:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:US54GJ4YDEH7QLK3HLQQ7FB5GW","target":"record","payload":{"canonical_record":{"source":{"id":"2206.15462","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T17:55:12Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"fb14dfdd1a131a51df748c65431f32fe6e7d022aae3806648cb741fc32ceaf79","abstract_canon_sha256":"e1ea7d06fba37448f2d00a515202ad2bd861ce6f2b96878712179cf0a25704c9"},"schema_version":"1.0"},"canonical_sha256":"a4bbc32798190ff82d5b3ae10f943d35b94e368d730b528de494608200654756","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:43.967980Z","signature_b64":"pNIVDNM51E78Puc1vLl4vm/ChLDit057HPEViLh88vvdGYfCz/QpyMhmsNji/bQoSPXdhXt5+80bvvhEc2shAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4bbc32798190ff82d5b3ae10f943d35b94e368d730b528de494608200654756","last_reissued_at":"2026-07-05T07:30:43.967459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:43.967459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.15462","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h43csLwCpcHq7ha3/3wz4aKh2dPB+hXakaBk1kfr5aDjDGlbl0vLrDmCr9hI6emWSiPLiLDAg9WanCG3PXqQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:49:56.781754Z"},"content_sha256":"dae263bfee9f583fbb7a873fac08d5d211710b0e4d913886070e801d76816c0b","schema_version":"1.0","event_id":"sha256:dae263bfee9f583fbb7a873fac08d5d211710b0e4d913886070e801d76816c0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:US54GJ4YDEH7QLK3HLQQ7FB5GW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Franck Dernoncourt, Kushal Kafle, Vicente Ordonez, Ziyan Yang","submitted_at":"2022-06-30T17:55:12Z","abstract_excerpt":"We propose a margin-based loss for tuning joint vision-language models so that their gradient-based explanations are consistent with region-level annotations provided by humans for relatively smaller grounding datasets. We refer to this objective as Attention Mask Consistency (AMC) and demonstrate that it produces superior visual grounding results than previous methods that rely on using vision-language models to score the outputs of object detectors. Particularly, a model trained with AMC on top of standard vision-language modeling objectives obtains a state-of-the-art accuracy of 86.49% in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15462","kind":"arxiv","version":4},"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/2206.15462/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":"2026-07-05T07:30:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nxv5gJGlluwUqg/VwVA7WfR7E5ekYF1PlarZx/wkDQcV2BWDwqhHPYS3mmeeomVRI6wHD8O7C0HwONMUTlnCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:49:56.782769Z"},"content_sha256":"ebaa82b5886df082056f83d00d6ca6493337aee43609a8f20a1d88e64a241fc6","schema_version":"1.0","event_id":"sha256:ebaa82b5886df082056f83d00d6ca6493337aee43609a8f20a1d88e64a241fc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/US54GJ4YDEH7QLK3HLQQ7FB5GW/bundle.json","state_url":"https://pith.science/pith/US54GJ4YDEH7QLK3HLQQ7FB5GW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/US54GJ4YDEH7QLK3HLQQ7FB5GW/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":"2026-08-10T13:49:56Z","links":{"resolver":"https://pith.science/pith/US54GJ4YDEH7QLK3HLQQ7FB5GW","bundle":"https://pith.science/pith/US54GJ4YDEH7QLK3HLQQ7FB5GW/bundle.json","state":"https://pith.science/pith/US54GJ4YDEH7QLK3HLQQ7FB5GW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/US54GJ4YDEH7QLK3HLQQ7FB5GW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:US54GJ4YDEH7QLK3HLQQ7FB5GW","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":"e1ea7d06fba37448f2d00a515202ad2bd861ce6f2b96878712179cf0a25704c9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T17:55:12Z","title_canon_sha256":"fb14dfdd1a131a51df748c65431f32fe6e7d022aae3806648cb741fc32ceaf79"},"schema_version":"1.0","source":{"id":"2206.15462","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15462","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15462v4","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15462","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"pith_short_12","alias_value":"US54GJ4YDEH7","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"pith_short_16","alias_value":"US54GJ4YDEH7QLK3","created_at":"2026-07-05T07:30:43Z"},{"alias_kind":"pith_short_8","alias_value":"US54GJ4Y","created_at":"2026-07-05T07:30:43Z"}],"graph_snapshots":[{"event_id":"sha256:ebaa82b5886df082056f83d00d6ca6493337aee43609a8f20a1d88e64a241fc6","target":"graph","created_at":"2026-07-05T07:30:43Z","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/2206.15462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a margin-based loss for tuning joint vision-language models so that their gradient-based explanations are consistent with region-level annotations provided by humans for relatively smaller grounding datasets. We refer to this objective as Attention Mask Consistency (AMC) and demonstrate that it produces superior visual grounding results than previous methods that rely on using vision-language models to score the outputs of object detectors. Particularly, a model trained with AMC on top of standard vision-language modeling objectives obtains a state-of-the-art accuracy of 86.49% in t","authors_text":"Franck Dernoncourt, Kushal Kafle, Vicente Ordonez, Ziyan Yang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T17:55:12Z","title":"Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15462","kind":"arxiv","version":4},"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:dae263bfee9f583fbb7a873fac08d5d211710b0e4d913886070e801d76816c0b","target":"record","created_at":"2026-07-05T07:30:43Z","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":"e1ea7d06fba37448f2d00a515202ad2bd861ce6f2b96878712179cf0a25704c9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T17:55:12Z","title_canon_sha256":"fb14dfdd1a131a51df748c65431f32fe6e7d022aae3806648cb741fc32ceaf79"},"schema_version":"1.0","source":{"id":"2206.15462","kind":"arxiv","version":4}},"canonical_sha256":"a4bbc32798190ff82d5b3ae10f943d35b94e368d730b528de494608200654756","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4bbc32798190ff82d5b3ae10f943d35b94e368d730b528de494608200654756","first_computed_at":"2026-07-05T07:30:43.967459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:43.967459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pNIVDNM51E78Puc1vLl4vm/ChLDit057HPEViLh88vvdGYfCz/QpyMhmsNji/bQoSPXdhXt5+80bvvhEc2shAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:43.967980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.15462","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dae263bfee9f583fbb7a873fac08d5d211710b0e4d913886070e801d76816c0b","sha256:ebaa82b5886df082056f83d00d6ca6493337aee43609a8f20a1d88e64a241fc6"],"state_sha256":"0a4299c361f8576650ccae1b70c7fb18945a5cfff1f73147fa397dd89898ba11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hDXRb/F8VXHYL0+bXu3P54kDa6Fs4+Xysh/qlXFboHZ8oBN3KvViGfIvf+B5xvuQBn3YLR/5f/96EDUrtn4SDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:49:56.790290Z","bundle_sha256":"4ada977d3b8f5576f702e5a6ac094409f28cf7697e58c247ead766d2500e407c"}}