{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2DRNVFYVQJJ5W4VQOVC3GZRUHK","short_pith_number":"pith:2DRNVFYV","canonical_record":{"source":{"id":"2109.02227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-06T03:38:52Z","cross_cats_sorted":[],"title_canon_sha256":"c95ce6a3ea0efe8677818075921cb25760f1e0814c2219f3a9ed732202cda492","abstract_canon_sha256":"bca2306cca2b17313a4889832db30a1ea98d56a2ef3d2b61a4d132303eead06f"},"schema_version":"1.0"},"canonical_sha256":"d0e2da97158253db72b07545b366343a88be3b361d25f40fde67d77dc556c0ef","source":{"kind":"arxiv","id":"2109.02227","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02227","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02227v1","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02227","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"2DRNVFYVQJJ5","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"2DRNVFYVQJJ5W4VQ","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"2DRNVFYV","created_at":"2026-07-05T03:11:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2DRNVFYVQJJ5W4VQOVC3GZRUHK","target":"record","payload":{"canonical_record":{"source":{"id":"2109.02227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-06T03:38:52Z","cross_cats_sorted":[],"title_canon_sha256":"c95ce6a3ea0efe8677818075921cb25760f1e0814c2219f3a9ed732202cda492","abstract_canon_sha256":"bca2306cca2b17313a4889832db30a1ea98d56a2ef3d2b61a4d132303eead06f"},"schema_version":"1.0"},"canonical_sha256":"d0e2da97158253db72b07545b366343a88be3b361d25f40fde67d77dc556c0ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:40.064390Z","signature_b64":"Uj9aShTdQd8r3cKJxmxtfHWJpdu8KB016b19yOcDiIBu6zYt7+xH6U6d22Ul7yudp2y3FXORKACbcBRYuGqhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0e2da97158253db72b07545b366343a88be3b361d25f40fde67d77dc556c0ef","last_reissued_at":"2026-07-05T03:11:40.064040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:40.064040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.02227","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":"2026-07-05T03:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OuDq+Oqrxkl77ucBxl6Lkdu9/LXpo2AAsZOI9yxup1tMFTL4615Z5rJ8SvSGiQNELNNQeu0ZTlX6AYHub4xhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:51:25.925376Z"},"content_sha256":"ab4b39159be57dfdf7b8e0562563a74706e34cc5740c4ba367d3eb023f3c5353","schema_version":"1.0","event_id":"sha256:ab4b39159be57dfdf7b8e0562563a74706e34cc5740c4ba367d3eb023f3c5353"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2DRNVFYVQJJ5W4VQOVC3GZRUHK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Generate Scene Graph from Natural Language Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Jianwei Yang, Jing Shi, Yin Li, Yiwu Zhong","submitted_at":"2021-09-06T03:38:52Z","abstract_excerpt":"Learning from image-text data has demonstrated recent success for many recognition tasks, yet is currently limited to visual features or individual visual concepts such as objects. In this paper, we propose one of the first methods that learn from image-sentence pairs to extract a graphical representation of localized objects and their relationships within an image, known as scene graph. To bridge the gap between images and texts, we leverage an off-the-shelf object detector to identify and localize object instances, match labels of detected regions to concepts parsed from captions, and thus c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02227","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.02227/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":"2026-07-05T03:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PjIu2ncR4jz2Z+6NhYExgr/CleTXPXLmKqZXGOEvsgT7RZOcVoBhG1RbaDPfLBs1DPb6yQMoMEhuLIu3x7wyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:51:25.926526Z"},"content_sha256":"213f570c0337398adcd4032f4b45589eaf92560726c5d68cf5b5ce1cb4af2620","schema_version":"1.0","event_id":"sha256:213f570c0337398adcd4032f4b45589eaf92560726c5d68cf5b5ce1cb4af2620"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2DRNVFYVQJJ5W4VQOVC3GZRUHK/bundle.json","state_url":"https://pith.science/pith/2DRNVFYVQJJ5W4VQOVC3GZRUHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2DRNVFYVQJJ5W4VQOVC3GZRUHK/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":"2026-08-24T00:51:25Z","links":{"resolver":"https://pith.science/pith/2DRNVFYVQJJ5W4VQOVC3GZRUHK","bundle":"https://pith.science/pith/2DRNVFYVQJJ5W4VQOVC3GZRUHK/bundle.json","state":"https://pith.science/pith/2DRNVFYVQJJ5W4VQOVC3GZRUHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2DRNVFYVQJJ5W4VQOVC3GZRUHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2DRNVFYVQJJ5W4VQOVC3GZRUHK","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":"bca2306cca2b17313a4889832db30a1ea98d56a2ef3d2b61a4d132303eead06f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-06T03:38:52Z","title_canon_sha256":"c95ce6a3ea0efe8677818075921cb25760f1e0814c2219f3a9ed732202cda492"},"schema_version":"1.0","source":{"id":"2109.02227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02227","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02227v1","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02227","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"2DRNVFYVQJJ5","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"2DRNVFYVQJJ5W4VQ","created_at":"2026-07-05T03:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"2DRNVFYV","created_at":"2026-07-05T03:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:213f570c0337398adcd4032f4b45589eaf92560726c5d68cf5b5ce1cb4af2620","target":"graph","created_at":"2026-07-05T03:11:40Z","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/2109.02227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from image-text data has demonstrated recent success for many recognition tasks, yet is currently limited to visual features or individual visual concepts such as objects. In this paper, we propose one of the first methods that learn from image-sentence pairs to extract a graphical representation of localized objects and their relationships within an image, known as scene graph. To bridge the gap between images and texts, we leverage an off-the-shelf object detector to identify and localize object instances, match labels of detected regions to concepts parsed from captions, and thus c","authors_text":"Chenliang Xu, Jianwei Yang, Jing Shi, Yin Li, Yiwu Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-06T03:38:52Z","title":"Learning to Generate Scene Graph from Natural Language Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02227","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:ab4b39159be57dfdf7b8e0562563a74706e34cc5740c4ba367d3eb023f3c5353","target":"record","created_at":"2026-07-05T03:11:40Z","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":"bca2306cca2b17313a4889832db30a1ea98d56a2ef3d2b61a4d132303eead06f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-06T03:38:52Z","title_canon_sha256":"c95ce6a3ea0efe8677818075921cb25760f1e0814c2219f3a9ed732202cda492"},"schema_version":"1.0","source":{"id":"2109.02227","kind":"arxiv","version":1}},"canonical_sha256":"d0e2da97158253db72b07545b366343a88be3b361d25f40fde67d77dc556c0ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0e2da97158253db72b07545b366343a88be3b361d25f40fde67d77dc556c0ef","first_computed_at":"2026-07-05T03:11:40.064040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:40.064040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uj9aShTdQd8r3cKJxmxtfHWJpdu8KB016b19yOcDiIBu6zYt7+xH6U6d22Ul7yudp2y3FXORKACbcBRYuGqhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:40.064390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab4b39159be57dfdf7b8e0562563a74706e34cc5740c4ba367d3eb023f3c5353","sha256:213f570c0337398adcd4032f4b45589eaf92560726c5d68cf5b5ce1cb4af2620"],"state_sha256":"da6491d060b5522af808fc98ff46f7e8c34cb6551216a1c2ef1af18a8295a960"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V2/tuX8BmRt4QeFjt11bL3TpOBU38JWPo0Z4eY/AnK8Naq4rMHXcEoCnBdHDzHcRcAaCJGW393N1O/n6yimICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T00:51:25.930874Z","bundle_sha256":"f1a2f016d8bcbe01f4f7a64db66b3d9d3948c0b788af03b1ed4774f0317d593e"}}