{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MRANN3OQYGZ5VVVPF5AASZLKLR","short_pith_number":"pith:MRANN3OQ","canonical_record":{"source":{"id":"2203.06907","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T08:01:14Z","cross_cats_sorted":[],"title_canon_sha256":"4f18db46aeec959c8addb9e9ea79b808bb261dea08d97235de5809f85c27a2a8","abstract_canon_sha256":"8e774c854b4273aee17549f205dc978a307805ae179ad72ece1d41ac82c0d972"},"schema_version":"1.0"},"canonical_sha256":"6440d6edd0c1b3dad6af2f4009656a5c74613ee1b85646ed14d7fffc919d5520","source":{"kind":"arxiv","id":"2203.06907","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06907","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06907v5","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06907","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"MRANN3OQYGZ5","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"MRANN3OQYGZ5VVVP","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"MRANN3OQ","created_at":"2026-07-05T07:03:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MRANN3OQYGZ5VVVPF5AASZLKLR","target":"record","payload":{"canonical_record":{"source":{"id":"2203.06907","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T08:01:14Z","cross_cats_sorted":[],"title_canon_sha256":"4f18db46aeec959c8addb9e9ea79b808bb261dea08d97235de5809f85c27a2a8","abstract_canon_sha256":"8e774c854b4273aee17549f205dc978a307805ae179ad72ece1d41ac82c0d972"},"schema_version":"1.0"},"canonical_sha256":"6440d6edd0c1b3dad6af2f4009656a5c74613ee1b85646ed14d7fffc919d5520","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:17.222372Z","signature_b64":"DjzfzcxEkGFrfkjJtP1bDit0DV9swiHcFGom4KmmMQwqlPKyKPC9E3kqAk7z60uAYv6oUJB7vzCzUpNVvqBmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6440d6edd0c1b3dad6af2f4009656a5c74613ee1b85646ed14d7fffc919d5520","last_reissued_at":"2026-07-05T07:03:17.221740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:17.221740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.06907","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9D1u6SrJnsQfuBgc8Odp+Nk6fqiX8/09uYt0sgzeLkrLo9inmZiVeIYpdPEp7H6cFEXKy/+VKy4hWygpSq2oBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:40.607215Z"},"content_sha256":"395ccfe293595b4dcd4015b4861eaa84c98a34229ddd3d1683e9b8c93c672fc0","schema_version":"1.0","event_id":"sha256:395ccfe293595b4dcd4015b4861eaa84c98a34229ddd3d1683e9b8c93c672fc0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MRANN3OQYGZ5VVVPF5AASZLKLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Wang, Jiayi Ma, Jingdong Chen, Xiang Xiang, Yansheng Li, Yongjun Zhang, Youming Deng","submitted_at":"2022-03-14T08:01:14Z","abstract_excerpt":"As far as Scene Graph Generation (SGG), coarse and fine predicates mix in the dataset due to the crowd-sourced labeling, and the long-tail problem is also pronounced. Given this tricky situation, many existing SGG methods treat the predicates equally and learn the model under the supervision of mixed-granularity predicates in one stage, leading to relatively coarse predictions. In order to alleviate the negative impact of the suboptimum mixed-granularity annotation and long-tail effect problems, this paper proposes a novel Hierarchical Memory Learning (HML) framework to learn the model from si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06907","kind":"arxiv","version":5},"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/2203.06907/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":"2026-07-05T07:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"okWRtMaF1O9GVhd0InbjsAGikAC3M8+8wtGDbPKpzkkm9Vb3rBdddab+pYaNWc0yeHx83Uxi6GTSKCVfbHjUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:40.607603Z"},"content_sha256":"0696fcf7c69c4eae61090774cd904649e0e53e572a6ede3762355c4146dd6d32","schema_version":"1.0","event_id":"sha256:0696fcf7c69c4eae61090774cd904649e0e53e572a6ede3762355c4146dd6d32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MRANN3OQYGZ5VVVPF5AASZLKLR/bundle.json","state_url":"https://pith.science/pith/MRANN3OQYGZ5VVVPF5AASZLKLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MRANN3OQYGZ5VVVPF5AASZLKLR/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":"2026-07-09T05:01:40Z","links":{"resolver":"https://pith.science/pith/MRANN3OQYGZ5VVVPF5AASZLKLR","bundle":"https://pith.science/pith/MRANN3OQYGZ5VVVPF5AASZLKLR/bundle.json","state":"https://pith.science/pith/MRANN3OQYGZ5VVVPF5AASZLKLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MRANN3OQYGZ5VVVPF5AASZLKLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MRANN3OQYGZ5VVVPF5AASZLKLR","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":"8e774c854b4273aee17549f205dc978a307805ae179ad72ece1d41ac82c0d972","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T08:01:14Z","title_canon_sha256":"4f18db46aeec959c8addb9e9ea79b808bb261dea08d97235de5809f85c27a2a8"},"schema_version":"1.0","source":{"id":"2203.06907","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06907","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06907v5","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06907","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"MRANN3OQYGZ5","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"MRANN3OQYGZ5VVVP","created_at":"2026-07-05T07:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"MRANN3OQ","created_at":"2026-07-05T07:03:17Z"}],"graph_snapshots":[{"event_id":"sha256:0696fcf7c69c4eae61090774cd904649e0e53e572a6ede3762355c4146dd6d32","target":"graph","created_at":"2026-07-05T07:03:17Z","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/2203.06907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As far as Scene Graph Generation (SGG), coarse and fine predicates mix in the dataset due to the crowd-sourced labeling, and the long-tail problem is also pronounced. Given this tricky situation, many existing SGG methods treat the predicates equally and learn the model under the supervision of mixed-granularity predicates in one stage, leading to relatively coarse predictions. In order to alleviate the negative impact of the suboptimum mixed-granularity annotation and long-tail effect problems, this paper proposes a novel Hierarchical Memory Learning (HML) framework to learn the model from si","authors_text":"Jian Wang, Jiayi Ma, Jingdong Chen, Xiang Xiang, Yansheng Li, Yongjun Zhang, Youming Deng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T08:01:14Z","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06907","kind":"arxiv","version":5},"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":"sha256:395ccfe293595b4dcd4015b4861eaa84c98a34229ddd3d1683e9b8c93c672fc0","target":"record","created_at":"2026-07-05T07:03:17Z","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":"8e774c854b4273aee17549f205dc978a307805ae179ad72ece1d41ac82c0d972","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T08:01:14Z","title_canon_sha256":"4f18db46aeec959c8addb9e9ea79b808bb261dea08d97235de5809f85c27a2a8"},"schema_version":"1.0","source":{"id":"2203.06907","kind":"arxiv","version":5}},"canonical_sha256":"6440d6edd0c1b3dad6af2f4009656a5c74613ee1b85646ed14d7fffc919d5520","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6440d6edd0c1b3dad6af2f4009656a5c74613ee1b85646ed14d7fffc919d5520","first_computed_at":"2026-07-05T07:03:17.221740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:17.221740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DjzfzcxEkGFrfkjJtP1bDit0DV9swiHcFGom4KmmMQwqlPKyKPC9E3kqAk7z60uAYv6oUJB7vzCzUpNVvqBmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:17.222372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06907","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:395ccfe293595b4dcd4015b4861eaa84c98a34229ddd3d1683e9b8c93c672fc0","sha256:0696fcf7c69c4eae61090774cd904649e0e53e572a6ede3762355c4146dd6d32"],"state_sha256":"c8da7a8c973bc9c1614b2e7da96bdf490f2049434973eec1dbc4463e731cd9a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gn9sR8hwVlScdVdD0PHlqLYrm45RTckno0ihWzj9CHFKCG1hFW8WyWa16k4kzrd0RtP6E/Wq6vT+TWDmXZnsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:01:40.609634Z","bundle_sha256":"011eb0b730f276f0de8810d86329a83c9e340495d3004087aa9e3a87fdfc232a"}}