{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QROXT2W6ZA3TRUBIJXC27U7SNB","short_pith_number":"pith:QROXT2W6","canonical_record":{"source":{"id":"1611.04246","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-14T04:13:37Z","cross_cats_sorted":[],"title_canon_sha256":"7caf905435463726acd96c795c935f10e16185d4592750f0b7845f10ec62dc73","abstract_canon_sha256":"a5d0ab56022f970f6e62169fee2d354bf05a7352fdff801a358fa180c0d6eeeb"},"schema_version":"1.0"},"canonical_sha256":"845d79eadec83738d0284dc5afd3f2684e16b0aff46412810f83f1456155e97b","source":{"kind":"arxiv","id":"1611.04246","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.04246","created_at":"2026-05-18T00:48:53Z"},{"alias_kind":"arxiv_version","alias_value":"1611.04246v2","created_at":"2026-05-18T00:48:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04246","created_at":"2026-05-18T00:48:53Z"},{"alias_kind":"pith_short_12","alias_value":"QROXT2W6ZA3T","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QROXT2W6ZA3TRUBI","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QROXT2W6","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QROXT2W6ZA3TRUBIJXC27U7SNB","target":"record","payload":{"canonical_record":{"source":{"id":"1611.04246","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-14T04:13:37Z","cross_cats_sorted":[],"title_canon_sha256":"7caf905435463726acd96c795c935f10e16185d4592750f0b7845f10ec62dc73","abstract_canon_sha256":"a5d0ab56022f970f6e62169fee2d354bf05a7352fdff801a358fa180c0d6eeeb"},"schema_version":"1.0"},"canonical_sha256":"845d79eadec83738d0284dc5afd3f2684e16b0aff46412810f83f1456155e97b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:53.718651Z","signature_b64":"KyUtjuMVHv2O9+ITt9jKfYitOCaI8nvCOFIew6HsCkKFbd6zHixk7YQ6J/AdIC1r6fvVgvjypXvAiJcAc1DzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"845d79eadec83738d0284dc5afd3f2684e16b0aff46412810f83f1456155e97b","last_reissued_at":"2026-05-18T00:48:53.717899Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:53.717899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.04246","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":"2026-05-18T00:48:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TWmixr9NoD8Kah7zxwprSbslJN3Nz00Qan3UmPjVEof+lUfO9PX3fA6RYdy54q6wjmBqnhrZdFfcbYOjBZdQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:32:40.087680Z"},"content_sha256":"30301b35181cc7d94ab8e7e8025de9a1eaec8669411b766b0caa604dd77fab68","schema_version":"1.0","event_id":"sha256:30301b35181cc7d94ab8e7e8025de9a1eaec8669411b766b0caa604dd77fab68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QROXT2W6ZA3TRUBIJXC27U7SNB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Quanshi Zhang, Ruiming Cao, Song-Chun Zhu, Ying Nian Wu","submitted_at":"2016-11-14T04:13:37Z","abstract_excerpt":"This paper proposes a learning strategy that extracts object-part concepts from a pre-trained convolutional neural network (CNN), in an attempt to 1) explore explicit semantics hidden in CNN units and 2) gradually grow a semantically interpretable graphical model on the pre-trained CNN for hierarchical object understanding. Given part annotations on very few (e.g., 3-12) objects, our method mines certain latent patterns from the pre-trained CNN and associates them with different semantic parts. We use a four-layer And-Or graph to organize the mined latent patterns, so as to clarify their inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04246","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":"2026-05-18T00:48:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vQEieESYuzBwUF0mpNnnnqv0EyVZCBMeeXcTryhKX2A9qujm+F1RJZsEKUoI4cfesn17PxnrhFDKv5zD6milCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:32:40.088233Z"},"content_sha256":"f19bcd3a41a0236d9b6fbfb2988e2e1795e39e9aed4f807aaaacaab398e86691","schema_version":"1.0","event_id":"sha256:f19bcd3a41a0236d9b6fbfb2988e2e1795e39e9aed4f807aaaacaab398e86691"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QROXT2W6ZA3TRUBIJXC27U7SNB/bundle.json","state_url":"https://pith.science/pith/QROXT2W6ZA3TRUBIJXC27U7SNB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QROXT2W6ZA3TRUBIJXC27U7SNB/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":"2026-05-28T22:32:40Z","links":{"resolver":"https://pith.science/pith/QROXT2W6ZA3TRUBIJXC27U7SNB","bundle":"https://pith.science/pith/QROXT2W6ZA3TRUBIJXC27U7SNB/bundle.json","state":"https://pith.science/pith/QROXT2W6ZA3TRUBIJXC27U7SNB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QROXT2W6ZA3TRUBIJXC27U7SNB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QROXT2W6ZA3TRUBIJXC27U7SNB","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":"a5d0ab56022f970f6e62169fee2d354bf05a7352fdff801a358fa180c0d6eeeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-14T04:13:37Z","title_canon_sha256":"7caf905435463726acd96c795c935f10e16185d4592750f0b7845f10ec62dc73"},"schema_version":"1.0","source":{"id":"1611.04246","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.04246","created_at":"2026-05-18T00:48:53Z"},{"alias_kind":"arxiv_version","alias_value":"1611.04246v2","created_at":"2026-05-18T00:48:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04246","created_at":"2026-05-18T00:48:53Z"},{"alias_kind":"pith_short_12","alias_value":"QROXT2W6ZA3T","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QROXT2W6ZA3TRUBI","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QROXT2W6","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:f19bcd3a41a0236d9b6fbfb2988e2e1795e39e9aed4f807aaaacaab398e86691","target":"graph","created_at":"2026-05-18T00:48:53Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"This paper proposes a learning strategy that extracts object-part concepts from a pre-trained convolutional neural network (CNN), in an attempt to 1) explore explicit semantics hidden in CNN units and 2) gradually grow a semantically interpretable graphical model on the pre-trained CNN for hierarchical object understanding. Given part annotations on very few (e.g., 3-12) objects, our method mines certain latent patterns from the pre-trained CNN and associates them with different semantic parts. We use a four-layer And-Or graph to organize the mined latent patterns, so as to clarify their inter","authors_text":"Quanshi Zhang, Ruiming Cao, Song-Chun Zhu, Ying Nian Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-14T04:13:37Z","title":"Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04246","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":"sha256:30301b35181cc7d94ab8e7e8025de9a1eaec8669411b766b0caa604dd77fab68","target":"record","created_at":"2026-05-18T00:48:53Z","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":"a5d0ab56022f970f6e62169fee2d354bf05a7352fdff801a358fa180c0d6eeeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-14T04:13:37Z","title_canon_sha256":"7caf905435463726acd96c795c935f10e16185d4592750f0b7845f10ec62dc73"},"schema_version":"1.0","source":{"id":"1611.04246","kind":"arxiv","version":2}},"canonical_sha256":"845d79eadec83738d0284dc5afd3f2684e16b0aff46412810f83f1456155e97b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"845d79eadec83738d0284dc5afd3f2684e16b0aff46412810f83f1456155e97b","first_computed_at":"2026-05-18T00:48:53.717899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:53.717899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KyUtjuMVHv2O9+ITt9jKfYitOCaI8nvCOFIew6HsCkKFbd6zHixk7YQ6J/AdIC1r6fvVgvjypXvAiJcAc1DzDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:53.718651Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.04246","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30301b35181cc7d94ab8e7e8025de9a1eaec8669411b766b0caa604dd77fab68","sha256:f19bcd3a41a0236d9b6fbfb2988e2e1795e39e9aed4f807aaaacaab398e86691"],"state_sha256":"ac512ec249f34356e61f50e55044a4c4120aef321de9703eda61dbaae52ecdf7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UEtOBw1L4QBzqr4yqhGXGnPCWCTHv8fpzisuSnEuTIhQLu2wEDd+hExpEK5X/DoqfifR2nffW5Bq2KgE1K+iDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T22:32:40.090474Z","bundle_sha256":"4bd9b96a84f8e6267b661ab5d34cdb2b1d2aa371527d045b6f68386738894879"}}