{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CEIP7LJHK2AEXM24OKPPJCPRPI","short_pith_number":"pith:CEIP7LJH","canonical_record":{"source":{"id":"1903.06150","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-14T17:52:18Z","cross_cats_sorted":[],"title_canon_sha256":"005ba7c69f848fc7c0d90e4a6f96ff413a3bd8e9b80608156530a4901c7b3890","abstract_canon_sha256":"7f6e593540251f478be4ab035ecefa9eaaf98e01ddf5b16e24f189a775129dea"},"schema_version":"1.0"},"canonical_sha256":"1110ffad2756804bb35c729ef489f17a147372d64ec9f976235f61476d61d7de","source":{"kind":"arxiv","id":"1903.06150","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.06150","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"1903.06150v2","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06150","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"CEIP7LJHK2AE","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"CEIP7LJHK2AEXM24","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"CEIP7LJH","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CEIP7LJHK2AEXM24OKPPJCPRPI","target":"record","payload":{"canonical_record":{"source":{"id":"1903.06150","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-14T17:52:18Z","cross_cats_sorted":[],"title_canon_sha256":"005ba7c69f848fc7c0d90e4a6f96ff413a3bd8e9b80608156530a4901c7b3890","abstract_canon_sha256":"7f6e593540251f478be4ab035ecefa9eaaf98e01ddf5b16e24f189a775129dea"},"schema_version":"1.0"},"canonical_sha256":"1110ffad2756804bb35c729ef489f17a147372d64ec9f976235f61476d61d7de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:42.429790Z","signature_b64":"9WRzOkZYuC9uUBkDmp5YX49A00WKLcaxVjFW9WTAZs+dRC/Iv7krKhtHtlxyXAWLBRidH40ifOCDBhUNZVDzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1110ffad2756804bb35c729ef489f17a147372d64ec9f976235f61476d61d7de","last_reissued_at":"2026-05-17T23:43:42.429064Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:42.429064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.06150","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":"2026-05-17T23:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cK6kSVRe7y2UOV1U3v4xMkf2ffpCktFK4sqIBzEHeixT2RaarzNXPM6lZ4+TBzAXVW2KMnXDQt9H+XLsdQe/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T00:11:26.611665Z"},"content_sha256":"32fbd1e9cc9395cd448b8d6c6699c82ee4ed82a0aac0cbca24602980c7520f34","schema_version":"1.0","event_id":"sha256:32fbd1e9cc9395cd448b8d6c6699c82ee4ed82a0aac0cbca24602980c7520f34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CEIP7LJHK2AEXM24OKPPJCPRPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heliang Zheng, Jianlong Fu, Jiebo Luo, Zheng-Jun Zha","submitted_at":"2019-03-14T17:52:18Z","abstract_excerpt":"Learning subtle yet discriminative features (e.g., beak and eyes for a bird) plays a significant role in fine-grained image recognition. Existing attention-based approaches localize and amplify significant parts to learn fine-grained details, which often suffer from a limited number of parts and heavy computational cost. In this paper, we propose to learn such fine-grained features from hundreds of part proposals by Trilinear Attention Sampling Network (TASN) in an efficient teacher-student manner. Specifically, TASN consists of 1) a trilinear attention module, which generates attention maps b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06150","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":""},"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":"2026-05-17T23:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"esX8TIgOXG42z/wiySdOTXbdBWpuMyrkt+Azopxr+VydBhGHyO5wk1KZcQGQIiGFGfUimsbp/x+RMNUd0PZgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T00:11:26.612008Z"},"content_sha256":"31ff173e216d6e386c52dc9a5945d85f6f7ac7728d5e6e0ba93b41baf1943b00","schema_version":"1.0","event_id":"sha256:31ff173e216d6e386c52dc9a5945d85f6f7ac7728d5e6e0ba93b41baf1943b00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CEIP7LJHK2AEXM24OKPPJCPRPI/bundle.json","state_url":"https://pith.science/pith/CEIP7LJHK2AEXM24OKPPJCPRPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CEIP7LJHK2AEXM24OKPPJCPRPI/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":"2026-05-25T00:11:26Z","links":{"resolver":"https://pith.science/pith/CEIP7LJHK2AEXM24OKPPJCPRPI","bundle":"https://pith.science/pith/CEIP7LJHK2AEXM24OKPPJCPRPI/bundle.json","state":"https://pith.science/pith/CEIP7LJHK2AEXM24OKPPJCPRPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CEIP7LJHK2AEXM24OKPPJCPRPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CEIP7LJHK2AEXM24OKPPJCPRPI","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":"7f6e593540251f478be4ab035ecefa9eaaf98e01ddf5b16e24f189a775129dea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-14T17:52:18Z","title_canon_sha256":"005ba7c69f848fc7c0d90e4a6f96ff413a3bd8e9b80608156530a4901c7b3890"},"schema_version":"1.0","source":{"id":"1903.06150","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.06150","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"1903.06150v2","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06150","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"CEIP7LJHK2AE","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"CEIP7LJHK2AEXM24","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"CEIP7LJH","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:31ff173e216d6e386c52dc9a5945d85f6f7ac7728d5e6e0ba93b41baf1943b00","target":"graph","created_at":"2026-05-17T23:43:42Z","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"},"paper":{"abstract_excerpt":"Learning subtle yet discriminative features (e.g., beak and eyes for a bird) plays a significant role in fine-grained image recognition. Existing attention-based approaches localize and amplify significant parts to learn fine-grained details, which often suffer from a limited number of parts and heavy computational cost. In this paper, we propose to learn such fine-grained features from hundreds of part proposals by Trilinear Attention Sampling Network (TASN) in an efficient teacher-student manner. Specifically, TASN consists of 1) a trilinear attention module, which generates attention maps b","authors_text":"Heliang Zheng, Jianlong Fu, Jiebo Luo, Zheng-Jun Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-14T17:52:18Z","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06150","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":"sha256:32fbd1e9cc9395cd448b8d6c6699c82ee4ed82a0aac0cbca24602980c7520f34","target":"record","created_at":"2026-05-17T23:43:42Z","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":"7f6e593540251f478be4ab035ecefa9eaaf98e01ddf5b16e24f189a775129dea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-14T17:52:18Z","title_canon_sha256":"005ba7c69f848fc7c0d90e4a6f96ff413a3bd8e9b80608156530a4901c7b3890"},"schema_version":"1.0","source":{"id":"1903.06150","kind":"arxiv","version":2}},"canonical_sha256":"1110ffad2756804bb35c729ef489f17a147372d64ec9f976235f61476d61d7de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1110ffad2756804bb35c729ef489f17a147372d64ec9f976235f61476d61d7de","first_computed_at":"2026-05-17T23:43:42.429064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:42.429064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9WRzOkZYuC9uUBkDmp5YX49A00WKLcaxVjFW9WTAZs+dRC/Iv7krKhtHtlxyXAWLBRidH40ifOCDBhUNZVDzDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:42.429790Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.06150","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32fbd1e9cc9395cd448b8d6c6699c82ee4ed82a0aac0cbca24602980c7520f34","sha256:31ff173e216d6e386c52dc9a5945d85f6f7ac7728d5e6e0ba93b41baf1943b00"],"state_sha256":"a6d3d1cb128b4bc85b127413015349a98e7f087df0fb9bb76f361370ce39dff8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9sxLBUERC5IZUz9jHca5iMspXACKaOCLqc+2+FUoFn5uYXWDGegL2jLOloq//b7FR9pM/OgwH5pMZT9BrbRjAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T00:11:26.614270Z","bundle_sha256":"a5b0c36ea581b20afd6aa73fd7830647e23a84b9f97ffc1a0c71f2d0c6482938"}}