{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D7FKJYJKJVZGVYKBLF5KGT5G77","short_pith_number":"pith:D7FKJYJK","canonical_record":{"source":{"id":"2510.14737","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T14:35:18Z","cross_cats_sorted":[],"title_canon_sha256":"c85882320849c4d4692746168094e519189c8a6ad98d90be1bed9d6d7b174313","abstract_canon_sha256":"6ec34a9be2c1667437ff299162eef65e51c6e0b2b019bababe3525d7f4b44d8b"},"schema_version":"1.0"},"canonical_sha256":"1fcaa4e12a4d726ae141597aa34fa6ffc2e88baa8410f0e5a5dc797674fe4ae6","source":{"kind":"arxiv","id":"2510.14737","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14737","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14737v3","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14737","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"D7FKJYJKJVZG","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"D7FKJYJKJVZGVYKB","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"D7FKJYJK","created_at":"2026-05-21T02:04:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D7FKJYJKJVZGVYKBLF5KGT5G77","target":"record","payload":{"canonical_record":{"source":{"id":"2510.14737","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T14:35:18Z","cross_cats_sorted":[],"title_canon_sha256":"c85882320849c4d4692746168094e519189c8a6ad98d90be1bed9d6d7b174313","abstract_canon_sha256":"6ec34a9be2c1667437ff299162eef65e51c6e0b2b019bababe3525d7f4b44d8b"},"schema_version":"1.0"},"canonical_sha256":"1fcaa4e12a4d726ae141597aa34fa6ffc2e88baa8410f0e5a5dc797674fe4ae6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:04:53.645067Z","signature_b64":"1MVgxG7d4rwhhvjn9zunm0VYkkfLlodE5y4Bca9lidvkU9qAff7U3H72OPruWopvDhLf3kJl1YC7hTZ+e8SrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fcaa4e12a4d726ae141597aa34fa6ffc2e88baa8410f0e5a5dc797674fe4ae6","last_reissued_at":"2026-05-21T02:04:53.644059Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:04:53.644059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.14737","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T02:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nRmnU+lCfahaRciZF1g64/Z5exHGn6OjVtz7bIBrSkBKf+8IU4BPLfgG1vNTqfx5gTaJrEFrhVSlR4RogwFCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:15:27.473041Z"},"content_sha256":"e0f83244672c9c0f677fdba4d11b7613294c7ba366e2895d319b1ee41e398cc2","schema_version":"1.0","event_id":"sha256:e0f83244672c9c0f677fdba4d11b7613294c7ba366e2895d319b1ee41e398cc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D7FKJYJKJVZGVYKBLF5KGT5G77","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Free-Grained Hierarchical Visual Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Hierarchical image recognition can learn consistent predictions from labels at any taxonomy level using mixed-granularity supervision.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Seulki Park, Stella X. Yu, Zilin Wang","submitted_at":"2025-10-16T14:35:18Z","abstract_excerpt":"Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the tidy assumption that every training image is fully annotated along its taxonomy path. Reality is messier: A distant bird may be labeled only bird, while a clear close-up may justify bald eagle. We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision. We build benchmark datasets with varying label granularity and sh"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That supplementing with broad text-based supervision or framing missing labels as semi-supervised learning will sufficiently compensate for incomplete annotations without introducing new inconsistencies or performance drops.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces free-grain hierarchical visual recognition with new benchmarks for mixed-granularity labels and methods using text-based supervision plus semi-supervised learning for missing labels.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hierarchical image recognition can learn consistent predictions from labels at any taxonomy level using mixed-granularity supervision.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ecc2df2a5f39c7120a0138065adc5771733e0b994f9e75424c5c98de4a7eab79"},"source":{"id":"2510.14737","kind":"arxiv","version":3},"verdict":{"id":"9ccae7e9-e5b9-4c86-837d-1e96404f9df3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T06:05:51.368233Z","strongest_claim":"We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision.","one_line_summary":"Introduces free-grain hierarchical visual recognition with new benchmarks for mixed-granularity labels and methods using text-based supervision plus semi-supervised learning for missing labels.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That supplementing with broad text-based supervision or framing missing labels as semi-supervised learning will sufficiently compensate for incomplete annotations without introducing new inconsistencies or performance drops.","pith_extraction_headline":"Hierarchical image recognition can learn consistent predictions from labels at any taxonomy level using mixed-granularity supervision."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.14737/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":2,"snapshot_sha256":"bdb70b7f470661db12862d79bbed1a1bff4b3215c171514a6023c4b44de56179"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"9ccae7e9-e5b9-4c86-837d-1e96404f9df3"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T02:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VNj5wa+C2Udthssa8Ih2U2CsesKNHcrt05xYWPhnNpdC/6FuUNK/Ur2ny3p8s29utwTQl2/mG7l0e2CyD2BiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:15:27.473930Z"},"content_sha256":"b154d1ea03f75ae086c070ab081e4b972df5ef7652ceebba7e80bd2815b804fe","schema_version":"1.0","event_id":"sha256:b154d1ea03f75ae086c070ab081e4b972df5ef7652ceebba7e80bd2815b804fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D7FKJYJKJVZGVYKBLF5KGT5G77/bundle.json","state_url":"https://pith.science/pith/D7FKJYJKJVZGVYKBLF5KGT5G77/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D7FKJYJKJVZGVYKBLF5KGT5G77/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":"2026-05-29T15:15:27Z","links":{"resolver":"https://pith.science/pith/D7FKJYJKJVZGVYKBLF5KGT5G77","bundle":"https://pith.science/pith/D7FKJYJKJVZGVYKBLF5KGT5G77/bundle.json","state":"https://pith.science/pith/D7FKJYJKJVZGVYKBLF5KGT5G77/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D7FKJYJKJVZGVYKBLF5KGT5G77/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D7FKJYJKJVZGVYKBLF5KGT5G77","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":"6ec34a9be2c1667437ff299162eef65e51c6e0b2b019bababe3525d7f4b44d8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T14:35:18Z","title_canon_sha256":"c85882320849c4d4692746168094e519189c8a6ad98d90be1bed9d6d7b174313"},"schema_version":"1.0","source":{"id":"2510.14737","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14737","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14737v3","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14737","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"D7FKJYJKJVZG","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"D7FKJYJKJVZGVYKB","created_at":"2026-05-21T02:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"D7FKJYJK","created_at":"2026-05-21T02:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:b154d1ea03f75ae086c070ab081e4b972df5ef7652ceebba7e80bd2815b804fe","target":"graph","created_at":"2026-05-21T02:04:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That supplementing with broad text-based supervision or framing missing labels as semi-supervised learning will sufficiently compensate for incomplete annotations without introducing new inconsistencies or performance drops."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Introduces free-grain hierarchical visual recognition with new benchmarks for mixed-granularity labels and methods using text-based supervision plus semi-supervised learning for missing labels."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Hierarchical image recognition can learn consistent predictions from labels at any taxonomy level using mixed-granularity supervision."}],"snapshot_sha256":"ecc2df2a5f39c7120a0138065adc5771733e0b994f9e75424c5c98de4a7eab79"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bdb70b7f470661db12862d79bbed1a1bff4b3215c171514a6023c4b44de56179"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.14737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the tidy assumption that every training image is fully annotated along its taxonomy path. Reality is messier: A distant bird may be labeled only bird, while a clear close-up may justify bald eagle. We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision. We build benchmark datasets with varying label granularity and sh","authors_text":"Seulki Park, Stella X. Yu, Zilin Wang","cross_cats":[],"headline":"Hierarchical image recognition can learn consistent predictions from labels at any taxonomy level using mixed-granularity supervision.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T14:35:18Z","title":"Free-Grained Hierarchical Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14737","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-18T06:05:51.368233Z","id":"9ccae7e9-e5b9-4c86-837d-1e96404f9df3","model_set":{"reader":"grok-4.3"},"one_line_summary":"Introduces free-grain hierarchical visual recognition with new benchmarks for mixed-granularity labels and methods using text-based supervision plus semi-supervised learning for missing labels.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Hierarchical image recognition can learn consistent predictions from labels at any taxonomy level using mixed-granularity supervision.","strongest_claim":"We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision.","weakest_assumption":"That supplementing with broad text-based supervision or framing missing labels as semi-supervised learning will sufficiently compensate for incomplete annotations without introducing new inconsistencies or performance drops."}},"verdict_id":"9ccae7e9-e5b9-4c86-837d-1e96404f9df3"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e0f83244672c9c0f677fdba4d11b7613294c7ba366e2895d319b1ee41e398cc2","target":"record","created_at":"2026-05-21T02:04:53Z","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":"6ec34a9be2c1667437ff299162eef65e51c6e0b2b019bababe3525d7f4b44d8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T14:35:18Z","title_canon_sha256":"c85882320849c4d4692746168094e519189c8a6ad98d90be1bed9d6d7b174313"},"schema_version":"1.0","source":{"id":"2510.14737","kind":"arxiv","version":3}},"canonical_sha256":"1fcaa4e12a4d726ae141597aa34fa6ffc2e88baa8410f0e5a5dc797674fe4ae6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fcaa4e12a4d726ae141597aa34fa6ffc2e88baa8410f0e5a5dc797674fe4ae6","first_computed_at":"2026-05-21T02:04:53.644059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:04:53.644059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1MVgxG7d4rwhhvjn9zunm0VYkkfLlodE5y4Bca9lidvkU9qAff7U3H72OPruWopvDhLf3kJl1YC7hTZ+e8SrDw==","signature_status":"signed_v1","signed_at":"2026-05-21T02:04:53.645067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.14737","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0f83244672c9c0f677fdba4d11b7613294c7ba366e2895d319b1ee41e398cc2","sha256:b154d1ea03f75ae086c070ab081e4b972df5ef7652ceebba7e80bd2815b804fe"],"state_sha256":"a836d88500e0712a139ed92c84d36f86b68a60735e5c0ec3fe02aee416ea23ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"888XkcCTJV+0tMDJIgEyqjLEmUQhnO76wWDDxh12m5IGCH4sXym28Qd9qFW9bNYYNS0hQA2h94lx9dy3UGc0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:15:27.478018Z","bundle_sha256":"1365218189f65fab24fc52d7bf935cf3b1277aa49f402680bf102af3a868d6e6"}}