{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UYBFTWST6IRTN2BPMXVCOOMFJY","short_pith_number":"pith:UYBFTWST","canonical_record":{"source":{"id":"1811.10770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T02:02:50Z","cross_cats_sorted":[],"title_canon_sha256":"dfe6d4913b8041b106a2ac44698580fd07f07d6859b68498c022f07d302f0967","abstract_canon_sha256":"fcd6a09af8108dec1f96203fcb8b6bba68fefd3fbe039623602a7d1b04a2dc60"},"schema_version":"1.0"},"canonical_sha256":"a60259da53f22336e82f65ea2739854e061cd47fae9f0cf2cac464f18b51142b","source":{"kind":"arxiv","id":"1811.10770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10770","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10770v1","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10770","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"pith_short_12","alias_value":"UYBFTWST6IRT","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UYBFTWST6IRTN2BP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UYBFTWST","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UYBFTWST6IRTN2BPMXVCOOMFJY","target":"record","payload":{"canonical_record":{"source":{"id":"1811.10770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T02:02:50Z","cross_cats_sorted":[],"title_canon_sha256":"dfe6d4913b8041b106a2ac44698580fd07f07d6859b68498c022f07d302f0967","abstract_canon_sha256":"fcd6a09af8108dec1f96203fcb8b6bba68fefd3fbe039623602a7d1b04a2dc60"},"schema_version":"1.0"},"canonical_sha256":"a60259da53f22336e82f65ea2739854e061cd47fae9f0cf2cac464f18b51142b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:47.587278Z","signature_b64":"+Uv5YTZeT1XdviG6SM5W5lNmLgnbmld3ZEtDt2N/XGYLnoX3yjaRaU5z7ZLr/hqqM/FIvicHk1RB/HVGNHm7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a60259da53f22336e82f65ea2739854e061cd47fae9f0cf2cac464f18b51142b","last_reissued_at":"2026-05-17T23:59:47.586900Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:47.586900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.10770","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":"2026-05-17T23:59:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cI4xEPC8piHpL22LF1ERsW4la4KK4GrvUUb9r+10R6Sp1Tcahoy1U9X4pFNhmywJXQ6b3SmAQKByp1FR8GiDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:34:38.457925Z"},"content_sha256":"feda46cece8b3bb32757d2aa02a0fc4c3d8c2b17909940d90540de3c04963c3b","schema_version":"1.0","event_id":"sha256:feda46cece8b3bb32757d2aa02a0fc4c3d8c2b17909940d90540de3c04963c3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UYBFTWST6IRTN2BPMXVCOOMFJY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Attention from Classifier Activations for Fine-grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rujie Liu, Wei Shen","submitted_at":"2018-11-27T02:02:50Z","abstract_excerpt":"Recent advances in fine-grained recognition utilize attention maps to localize objects of interest. Although there are many ways to generate attention maps, most of them rely on sophisticated loss functions or complex training processes. In this work, we propose a simple and straightforward attention generation model based on the output activations of classifiers. The advantage of our model is that it can be easily trained with image level labels and softmax loss functions. More specifically, multiple linear local classifiers are firstly adopted to perform fine-grained classification at each l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10770","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":""},"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":"2026-05-17T23:59:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0wVIP2OjYh0h4fMShr8OclT6liW9ppbjIEjaL55ETws41VKoBecww5IVwBNs+d4rssfHD2Au0Mjab//cIciwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:34:38.458277Z"},"content_sha256":"6d19588ff87f6f3ca86d938116e9c7eb8a5a83e5c139ec028b7bade41ac8be5e","schema_version":"1.0","event_id":"sha256:6d19588ff87f6f3ca86d938116e9c7eb8a5a83e5c139ec028b7bade41ac8be5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYBFTWST6IRTN2BPMXVCOOMFJY/bundle.json","state_url":"https://pith.science/pith/UYBFTWST6IRTN2BPMXVCOOMFJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYBFTWST6IRTN2BPMXVCOOMFJY/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":"2026-06-04T15:34:38Z","links":{"resolver":"https://pith.science/pith/UYBFTWST6IRTN2BPMXVCOOMFJY","bundle":"https://pith.science/pith/UYBFTWST6IRTN2BPMXVCOOMFJY/bundle.json","state":"https://pith.science/pith/UYBFTWST6IRTN2BPMXVCOOMFJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYBFTWST6IRTN2BPMXVCOOMFJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UYBFTWST6IRTN2BPMXVCOOMFJY","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":"fcd6a09af8108dec1f96203fcb8b6bba68fefd3fbe039623602a7d1b04a2dc60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T02:02:50Z","title_canon_sha256":"dfe6d4913b8041b106a2ac44698580fd07f07d6859b68498c022f07d302f0967"},"schema_version":"1.0","source":{"id":"1811.10770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10770","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10770v1","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10770","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"pith_short_12","alias_value":"UYBFTWST6IRT","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UYBFTWST6IRTN2BP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UYBFTWST","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:6d19588ff87f6f3ca86d938116e9c7eb8a5a83e5c139ec028b7bade41ac8be5e","target":"graph","created_at":"2026-05-17T23:59:47Z","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":"Recent advances in fine-grained recognition utilize attention maps to localize objects of interest. Although there are many ways to generate attention maps, most of them rely on sophisticated loss functions or complex training processes. In this work, we propose a simple and straightforward attention generation model based on the output activations of classifiers. The advantage of our model is that it can be easily trained with image level labels and softmax loss functions. More specifically, multiple linear local classifiers are firstly adopted to perform fine-grained classification at each l","authors_text":"Rujie Liu, Wei Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T02:02:50Z","title":"Generating Attention from Classifier Activations for Fine-grained Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10770","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:feda46cece8b3bb32757d2aa02a0fc4c3d8c2b17909940d90540de3c04963c3b","target":"record","created_at":"2026-05-17T23:59:47Z","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":"fcd6a09af8108dec1f96203fcb8b6bba68fefd3fbe039623602a7d1b04a2dc60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T02:02:50Z","title_canon_sha256":"dfe6d4913b8041b106a2ac44698580fd07f07d6859b68498c022f07d302f0967"},"schema_version":"1.0","source":{"id":"1811.10770","kind":"arxiv","version":1}},"canonical_sha256":"a60259da53f22336e82f65ea2739854e061cd47fae9f0cf2cac464f18b51142b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a60259da53f22336e82f65ea2739854e061cd47fae9f0cf2cac464f18b51142b","first_computed_at":"2026-05-17T23:59:47.586900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:47.586900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Uv5YTZeT1XdviG6SM5W5lNmLgnbmld3ZEtDt2N/XGYLnoX3yjaRaU5z7ZLr/hqqM/FIvicHk1RB/HVGNHm7Aw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:47.587278Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feda46cece8b3bb32757d2aa02a0fc4c3d8c2b17909940d90540de3c04963c3b","sha256:6d19588ff87f6f3ca86d938116e9c7eb8a5a83e5c139ec028b7bade41ac8be5e"],"state_sha256":"7adc446dd18ea3b44961246f21704c8e31bee61e189d165a8dcd14fae34b04a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OJwoPxOYro3NsyPVv+zDLUAqtNpf4ov2k7lMgZoAX2McU+i8WG5AeHQ4h6KMrxBimqS7l6uXcYB+zCi3aTfgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T15:34:38.460490Z","bundle_sha256":"b8ad1e9e3e279f49564fc3e95cf983eed30442f5ccef95db10119f225514c409"}}