{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JB5SGVL3WCYPRJJ4LRTKH3MFFD","short_pith_number":"pith:JB5SGVL3","canonical_record":{"source":{"id":"2002.12204","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-27T15:51:19Z","cross_cats_sorted":[],"title_canon_sha256":"a0d1c95ff8ea5c061f0d70539c291599af360afc8a4f773cb79b6e5cc5a50e02","abstract_canon_sha256":"408bcaf0824030f8379ea0a0d0098ffcfc05bbec9611918342e7f44363c94c48"},"schema_version":"1.0"},"canonical_sha256":"487b23557bb0b0f8a53c5c66a3ed8528c62b458cc3bb557c4d377fba167889a7","source":{"kind":"arxiv","id":"2002.12204","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12204","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12204v3","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12204","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"pith_short_12","alias_value":"JB5SGVL3WCYP","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"pith_short_16","alias_value":"JB5SGVL3WCYPRJJ4","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"pith_short_8","alias_value":"JB5SGVL3","created_at":"2026-07-05T00:58:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JB5SGVL3WCYPRJJ4LRTKH3MFFD","target":"record","payload":{"canonical_record":{"source":{"id":"2002.12204","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-27T15:51:19Z","cross_cats_sorted":[],"title_canon_sha256":"a0d1c95ff8ea5c061f0d70539c291599af360afc8a4f773cb79b6e5cc5a50e02","abstract_canon_sha256":"408bcaf0824030f8379ea0a0d0098ffcfc05bbec9611918342e7f44363c94c48"},"schema_version":"1.0"},"canonical_sha256":"487b23557bb0b0f8a53c5c66a3ed8528c62b458cc3bb557c4d377fba167889a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:08.362221Z","signature_b64":"/zm7A/F8+9/XfysAliGxYHX3yku9QENVDV6loSlQG9ckguJ1iLt8WzPCLHx2IBtHYVmhV6EcBeEheRlIfaOhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"487b23557bb0b0f8a53c5c66a3ed8528c62b458cc3bb557c4d377fba167889a7","last_reissued_at":"2026-07-05T00:58:08.361805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:08.361805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.12204","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":"2026-07-05T00:58:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTH30tfw13Y4GJpS/HPRao0hYtJWRDYH2YmSeXbhNFuv4gqpHmCefVtURVeAzMCftTJ8kaSy5F1C/dZvynDuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:45:46.159268Z"},"content_sha256":"cb8faf75ab530ed512cf0a479ef85ee4ebbd267553450b6336d9810bd9f58f7f","schema_version":"1.0","event_id":"sha256:cb8faf75ab530ed512cf0a479ef85ee4ebbd267553450b6336d9810bd9f58f7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JB5SGVL3WCYPRJJ4LRTKH3MFFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Commonsense R-CNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Jianqiang Huang, Qianru Sun, Tan Wang","submitted_at":"2020-02-27T15:51:19Z","abstract_excerpt":"We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12204","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.12204/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":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":"2026-07-05T00:58:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mVF2xoCsCUJnIgeLLqRg/6zeYxUNNTvOg5YMtOE69G+S5zW9HAOSz61H0ywthttnCmXQtKJC0L+IFkEFIqnuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:45:46.159643Z"},"content_sha256":"8fe9083c295da7ed0572b4723bd3494698b76040792cfe8175ad721093276231","schema_version":"1.0","event_id":"sha256:8fe9083c295da7ed0572b4723bd3494698b76040792cfe8175ad721093276231"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JB5SGVL3WCYPRJJ4LRTKH3MFFD/bundle.json","state_url":"https://pith.science/pith/JB5SGVL3WCYPRJJ4LRTKH3MFFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JB5SGVL3WCYPRJJ4LRTKH3MFFD/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":"2026-07-17T07:45:46Z","links":{"resolver":"https://pith.science/pith/JB5SGVL3WCYPRJJ4LRTKH3MFFD","bundle":"https://pith.science/pith/JB5SGVL3WCYPRJJ4LRTKH3MFFD/bundle.json","state":"https://pith.science/pith/JB5SGVL3WCYPRJJ4LRTKH3MFFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JB5SGVL3WCYPRJJ4LRTKH3MFFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JB5SGVL3WCYPRJJ4LRTKH3MFFD","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":"408bcaf0824030f8379ea0a0d0098ffcfc05bbec9611918342e7f44363c94c48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-27T15:51:19Z","title_canon_sha256":"a0d1c95ff8ea5c061f0d70539c291599af360afc8a4f773cb79b6e5cc5a50e02"},"schema_version":"1.0","source":{"id":"2002.12204","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12204","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12204v3","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12204","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"pith_short_12","alias_value":"JB5SGVL3WCYP","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"pith_short_16","alias_value":"JB5SGVL3WCYPRJJ4","created_at":"2026-07-05T00:58:08Z"},{"alias_kind":"pith_short_8","alias_value":"JB5SGVL3","created_at":"2026-07-05T00:58:08Z"}],"graph_snapshots":[{"event_id":"sha256:8fe9083c295da7ed0572b4723bd3494698b76040792cfe8175ad721093276231","target":"graph","created_at":"2026-07-05T00:58:08Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.12204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), whil","authors_text":"Hanwang Zhang, Jianqiang Huang, Qianru Sun, Tan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-27T15:51:19Z","title":"Visual Commonsense R-CNN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12204","kind":"arxiv","version":3},"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:cb8faf75ab530ed512cf0a479ef85ee4ebbd267553450b6336d9810bd9f58f7f","target":"record","created_at":"2026-07-05T00:58:08Z","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":"408bcaf0824030f8379ea0a0d0098ffcfc05bbec9611918342e7f44363c94c48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-27T15:51:19Z","title_canon_sha256":"a0d1c95ff8ea5c061f0d70539c291599af360afc8a4f773cb79b6e5cc5a50e02"},"schema_version":"1.0","source":{"id":"2002.12204","kind":"arxiv","version":3}},"canonical_sha256":"487b23557bb0b0f8a53c5c66a3ed8528c62b458cc3bb557c4d377fba167889a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"487b23557bb0b0f8a53c5c66a3ed8528c62b458cc3bb557c4d377fba167889a7","first_computed_at":"2026-07-05T00:58:08.361805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:08.361805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/zm7A/F8+9/XfysAliGxYHX3yku9QENVDV6loSlQG9ckguJ1iLt8WzPCLHx2IBtHYVmhV6EcBeEheRlIfaOhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:08.362221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.12204","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb8faf75ab530ed512cf0a479ef85ee4ebbd267553450b6336d9810bd9f58f7f","sha256:8fe9083c295da7ed0572b4723bd3494698b76040792cfe8175ad721093276231"],"state_sha256":"fbed9e4e415a67ef4dfa51d64ae91b8f545dd2c0f4db40ebe420a1664e36c342"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BYfBlL/81VrpY0za5skByyV/JPLjKryAPWKJd5GurGKiUqqtdfV/3c8LvKurazs5+W0tAmQ9yDIZdIf/eAfHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T07:45:46.161580Z","bundle_sha256":"ae0f54d69e3a7530b086c02f7a6a5b55284d2e40a3814143938156dd2e12b349"}}