{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ZH4HUIG6YPG57SAGKTDCVBBXKB","short_pith_number":"pith:ZH4HUIG6","canonical_record":{"source":{"id":"1512.02665","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2015-12-08T21:18:35Z","cross_cats_sorted":[],"title_canon_sha256":"a83af877e34a16e9a6e1c3842bce4bf451f3cdb523cae25d9a48b7a690876e07","abstract_canon_sha256":"2be12063e28bd2ff7f01b923d783e3d77891053871351d306fac518744f1baf0"},"schema_version":"1.0"},"canonical_sha256":"c9f87a20dec3cddfc80654c62a8437507656b9a708525fdbe51a9836a049d5ec","source":{"kind":"arxiv","id":"1512.02665","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.02665","created_at":"2026-05-18T01:24:37Z"},{"alias_kind":"arxiv_version","alias_value":"1512.02665v2","created_at":"2026-05-18T01:24:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.02665","created_at":"2026-05-18T01:24:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZH4HUIG6YPG5","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZH4HUIG6YPG57SAG","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZH4HUIG6","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ZH4HUIG6YPG57SAGKTDCVBBXKB","target":"record","payload":{"canonical_record":{"source":{"id":"1512.02665","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2015-12-08T21:18:35Z","cross_cats_sorted":[],"title_canon_sha256":"a83af877e34a16e9a6e1c3842bce4bf451f3cdb523cae25d9a48b7a690876e07","abstract_canon_sha256":"2be12063e28bd2ff7f01b923d783e3d77891053871351d306fac518744f1baf0"},"schema_version":"1.0"},"canonical_sha256":"c9f87a20dec3cddfc80654c62a8437507656b9a708525fdbe51a9836a049d5ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:37.946795Z","signature_b64":"GEUoKi1E78Ie2DhMiBXfHMpLYvibJ2ZI5O62xUUKPVJ9yigCWW4bYTLl6DGjt+v86gyrXFIN9sCd/E3Wuh7RCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9f87a20dec3cddfc80654c62a8437507656b9a708525fdbe51a9836a049d5ec","last_reissued_at":"2026-05-18T01:24:37.946358Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:37.946358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.02665","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":"2026-05-18T01:24:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ycNXOJcRotC/NOYIIvmcdn6jm1Fx4yx0n9O9tnD1AfZterx2dJt4Bflto8Y1I2dvngxE81E5lCUIuC+9kJkMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:37:37.691734Z"},"content_sha256":"f4cf9c81d01259cede64f8a84883560fc311f94244dd0140b75d4a517ea55fbb","schema_version":"1.0","event_id":"sha256:f4cf9c81d01259cede64f8a84883560fc311f94244dd0140b75d4a517ea55fbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ZH4HUIG6YPG57SAGKTDCVBBXKB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-grained Image Classification by Exploring Bipartite-Graph Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhou, Yuanqing Lin","submitted_at":"2015-12-08T21:18:35Z","abstract_excerpt":"Given a food image, can a fine-grained object recognition engine tell \"which restaurant which dish\" the food belongs to? Such ultra-fine grained image recognition is the key for many applications like search by images, but it is very challenging because it needs to discern subtle difference between classes while dealing with the scarcity of training data. Fortunately, the ultra-fine granularity naturally brings rich relationships among object classes. This paper proposes a novel approach to exploit the rich relationships through bipartite-graph labels (BGL). We show how to model BGL in an over"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.02665","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":"2026-05-18T01:24:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I4I0+TmL5ljUhj2jqNHwlg5q5+LK6dxZxqFqhPwHMLQhSHMebf128BEoNPnJfRZmdZlcR1YW+3D1AfRKSJNdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:37:37.692488Z"},"content_sha256":"bc2c793e7c72c448d14599e4ce46948a9daf4e0291c1d46ed39c160b6944ae83","schema_version":"1.0","event_id":"sha256:bc2c793e7c72c448d14599e4ce46948a9daf4e0291c1d46ed39c160b6944ae83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZH4HUIG6YPG57SAGKTDCVBBXKB/bundle.json","state_url":"https://pith.science/pith/ZH4HUIG6YPG57SAGKTDCVBBXKB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZH4HUIG6YPG57SAGKTDCVBBXKB/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":"2026-05-30T07:37:37Z","links":{"resolver":"https://pith.science/pith/ZH4HUIG6YPG57SAGKTDCVBBXKB","bundle":"https://pith.science/pith/ZH4HUIG6YPG57SAGKTDCVBBXKB/bundle.json","state":"https://pith.science/pith/ZH4HUIG6YPG57SAGKTDCVBBXKB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZH4HUIG6YPG57SAGKTDCVBBXKB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ZH4HUIG6YPG57SAGKTDCVBBXKB","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":"2be12063e28bd2ff7f01b923d783e3d77891053871351d306fac518744f1baf0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2015-12-08T21:18:35Z","title_canon_sha256":"a83af877e34a16e9a6e1c3842bce4bf451f3cdb523cae25d9a48b7a690876e07"},"schema_version":"1.0","source":{"id":"1512.02665","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.02665","created_at":"2026-05-18T01:24:37Z"},{"alias_kind":"arxiv_version","alias_value":"1512.02665v2","created_at":"2026-05-18T01:24:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.02665","created_at":"2026-05-18T01:24:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZH4HUIG6YPG5","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZH4HUIG6YPG57SAG","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZH4HUIG6","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:bc2c793e7c72c448d14599e4ce46948a9daf4e0291c1d46ed39c160b6944ae83","target":"graph","created_at":"2026-05-18T01:24:37Z","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":"Given a food image, can a fine-grained object recognition engine tell \"which restaurant which dish\" the food belongs to? Such ultra-fine grained image recognition is the key for many applications like search by images, but it is very challenging because it needs to discern subtle difference between classes while dealing with the scarcity of training data. Fortunately, the ultra-fine granularity naturally brings rich relationships among object classes. This paper proposes a novel approach to exploit the rich relationships through bipartite-graph labels (BGL). We show how to model BGL in an over","authors_text":"Feng Zhou, Yuanqing Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2015-12-08T21:18:35Z","title":"Fine-grained Image Classification by Exploring Bipartite-Graph Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.02665","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:f4cf9c81d01259cede64f8a84883560fc311f94244dd0140b75d4a517ea55fbb","target":"record","created_at":"2026-05-18T01:24:37Z","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":"2be12063e28bd2ff7f01b923d783e3d77891053871351d306fac518744f1baf0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2015-12-08T21:18:35Z","title_canon_sha256":"a83af877e34a16e9a6e1c3842bce4bf451f3cdb523cae25d9a48b7a690876e07"},"schema_version":"1.0","source":{"id":"1512.02665","kind":"arxiv","version":2}},"canonical_sha256":"c9f87a20dec3cddfc80654c62a8437507656b9a708525fdbe51a9836a049d5ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9f87a20dec3cddfc80654c62a8437507656b9a708525fdbe51a9836a049d5ec","first_computed_at":"2026-05-18T01:24:37.946358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:24:37.946358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GEUoKi1E78Ie2DhMiBXfHMpLYvibJ2ZI5O62xUUKPVJ9yigCWW4bYTLl6DGjt+v86gyrXFIN9sCd/E3Wuh7RCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:24:37.946795Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.02665","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4cf9c81d01259cede64f8a84883560fc311f94244dd0140b75d4a517ea55fbb","sha256:bc2c793e7c72c448d14599e4ce46948a9daf4e0291c1d46ed39c160b6944ae83"],"state_sha256":"82ef34930d425721f06aa62f6f5653af5a9f01df6e3971fcb14b944d4b3bf167"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6IAT8BYccD6OAQrjrRPeyfAImfhNL1Ei5lnmPyxMeacTAzFnwdD94J/g4C0RwAXwLfUS1hb5m1HXsgi6ijNICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:37:37.696101Z","bundle_sha256":"474b2e5f6b77782c0123f05dac682b9c668dbfa901601c3ca3d51cf05e23a25a"}}