{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XCBB3NZQ2Q272FG3GMBFFDKPS4","short_pith_number":"pith:XCBB3NZQ","canonical_record":{"source":{"id":"2108.08728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T14:53:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2b91e5379604766773c84d8b4d8b8f3ec9ef625da1bf2f73a6bfa67f7152c40a","abstract_canon_sha256":"9524be47bb534be4ee7ef88ee3cff4f677ecd4a6c1d99c478eb2b33fd46a9d2b"},"schema_version":"1.0"},"canonical_sha256":"b8821db730d435fd14db3302528d4f9736d79df808b02af633ceed907eaa3f76","source":{"kind":"arxiv","id":"2108.08728","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08728","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08728v2","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08728","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"XCBB3NZQ2Q27","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"XCBB3NZQ2Q272FG3","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"XCBB3NZQ","created_at":"2026-07-05T03:25:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XCBB3NZQ2Q272FG3GMBFFDKPS4","target":"record","payload":{"canonical_record":{"source":{"id":"2108.08728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T14:53:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2b91e5379604766773c84d8b4d8b8f3ec9ef625da1bf2f73a6bfa67f7152c40a","abstract_canon_sha256":"9524be47bb534be4ee7ef88ee3cff4f677ecd4a6c1d99c478eb2b33fd46a9d2b"},"schema_version":"1.0"},"canonical_sha256":"b8821db730d435fd14db3302528d4f9736d79df808b02af633ceed907eaa3f76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:34.119110Z","signature_b64":"jzTAvlfBrpcggWfkYwh3DRvtYlEgdxba2+CxvCJST3ST1ncBIechzb7xPlXAe3CfJsDdawjWpMTSyV4XVpjCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8821db730d435fd14db3302528d4f9736d79df808b02af633ceed907eaa3f76","last_reissued_at":"2026-07-05T03:25:34.118677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:34.118677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.08728","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":"2026-07-05T03:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YDPKjKrdbolIl3B5rIi0l2Arj/NalFzFyZXzU5TGrd8/mIfqNDKVjqfXjErGxocek0TBNGKiMLdqaKiahNd7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:32:41.253884Z"},"content_sha256":"73ca0d42f5afecb4393e809c5aa61d8851be7ed0104ef627a1bf265033c694e5","schema_version":"1.0","event_id":"sha256:73ca0d42f5afecb4393e809c5aa61d8851be7ed0104ef627a1bf265033c694e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XCBB3NZQ2Q272FG3GMBFFDKPS4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangyi Chen, Jie Zhou, Jiwen Lu, Yongming Rao","submitted_at":"2021-08-19T14:53:40Z","abstract_excerpt":"Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more effective attention based on causal inference. Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process. Specifically, we analyze the effect of the learned visual attention on network prediction through c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08728","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/2108.08728/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":"2026-07-05T03:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"voWYsUXaBKmqWmjsz+2dmYXKDDJ2jqQozcSWH1OMSgIhGbnq31zZQ3FjP36r12niyMPO6PMIfvJtDTDHzdPeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:32:41.254774Z"},"content_sha256":"32a20bf4e2f22b1b747fed8a24c63cbdd83f1b94e2a2878d6aea5ff0dbb399ff","schema_version":"1.0","event_id":"sha256:32a20bf4e2f22b1b747fed8a24c63cbdd83f1b94e2a2878d6aea5ff0dbb399ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCBB3NZQ2Q272FG3GMBFFDKPS4/bundle.json","state_url":"https://pith.science/pith/XCBB3NZQ2Q272FG3GMBFFDKPS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCBB3NZQ2Q272FG3GMBFFDKPS4/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":"2026-08-10T12:32:41Z","links":{"resolver":"https://pith.science/pith/XCBB3NZQ2Q272FG3GMBFFDKPS4","bundle":"https://pith.science/pith/XCBB3NZQ2Q272FG3GMBFFDKPS4/bundle.json","state":"https://pith.science/pith/XCBB3NZQ2Q272FG3GMBFFDKPS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCBB3NZQ2Q272FG3GMBFFDKPS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XCBB3NZQ2Q272FG3GMBFFDKPS4","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":"9524be47bb534be4ee7ef88ee3cff4f677ecd4a6c1d99c478eb2b33fd46a9d2b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T14:53:40Z","title_canon_sha256":"2b91e5379604766773c84d8b4d8b8f3ec9ef625da1bf2f73a6bfa67f7152c40a"},"schema_version":"1.0","source":{"id":"2108.08728","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08728","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08728v2","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08728","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"XCBB3NZQ2Q27","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"XCBB3NZQ2Q272FG3","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"XCBB3NZQ","created_at":"2026-07-05T03:25:34Z"}],"graph_snapshots":[{"event_id":"sha256:32a20bf4e2f22b1b747fed8a24c63cbdd83f1b94e2a2878d6aea5ff0dbb399ff","target":"graph","created_at":"2026-07-05T03:25:34Z","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/2108.08728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more effective attention based on causal inference. Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process. Specifically, we analyze the effect of the learned visual attention on network prediction through c","authors_text":"Guangyi Chen, Jie Zhou, Jiwen Lu, Yongming Rao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T14:53:40Z","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08728","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":"sha256:73ca0d42f5afecb4393e809c5aa61d8851be7ed0104ef627a1bf265033c694e5","target":"record","created_at":"2026-07-05T03:25:34Z","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":"9524be47bb534be4ee7ef88ee3cff4f677ecd4a6c1d99c478eb2b33fd46a9d2b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T14:53:40Z","title_canon_sha256":"2b91e5379604766773c84d8b4d8b8f3ec9ef625da1bf2f73a6bfa67f7152c40a"},"schema_version":"1.0","source":{"id":"2108.08728","kind":"arxiv","version":2}},"canonical_sha256":"b8821db730d435fd14db3302528d4f9736d79df808b02af633ceed907eaa3f76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8821db730d435fd14db3302528d4f9736d79df808b02af633ceed907eaa3f76","first_computed_at":"2026-07-05T03:25:34.118677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:34.118677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jzTAvlfBrpcggWfkYwh3DRvtYlEgdxba2+CxvCJST3ST1ncBIechzb7xPlXAe3CfJsDdawjWpMTSyV4XVpjCAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:34.119110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.08728","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73ca0d42f5afecb4393e809c5aa61d8851be7ed0104ef627a1bf265033c694e5","sha256:32a20bf4e2f22b1b747fed8a24c63cbdd83f1b94e2a2878d6aea5ff0dbb399ff"],"state_sha256":"2be0d01a4d4ace2ed9e91bb29b3e5fb88a6c36a66437f20734e62b9299fcbafa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5I9JTdaQpr6wejphAPKwUsHp3bgXVn6uT1i4Scjchuhpk6yXeL9a/z1DIIrSoZVrv9F88gUrf9E3kgeir0lECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:32:41.260364Z","bundle_sha256":"81773c02ef43442795b6baea8609f76cae6494e490ef9bedf769ded4814d0266"}}