{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RVXUIIQ2OHTXUYA2ZQ5W7XXFT4","short_pith_number":"pith:RVXUIIQ2","schema_version":"1.0","canonical_sha256":"8d6f44221a71e77a601acc3b6fdee59f35bd38a15e686995d04227e38b9d21da","source":{"kind":"arxiv","id":"2210.08675","version":1},"attestation_state":"computed","paper":{"title":"SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Woo Suk Choi, Yu-Jung Heo","submitted_at":"2022-10-17T00:37:00Z","abstract_excerpt":"Scene graph is structured semantic representation that can be modeled as a form of graph from images and texts. Image-based scene graph generation research has been actively conducted until recently, whereas text-based scene graph generation research has not. In this paper, we focus on the problem of scene graph parsing from textual description of a visual scene. The core idea is to use abstract meaning representation (AMR) instead of the dependency parsing mainly used in previous studies. AMR is a graph-based semantic formalism of natural language which abstracts concepts of words in a senten"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.08675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T00:37:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"55f9c2709a8cdc22c6475a79b7bc04baf47871db8a6d5b765e22bedcb967a02c","abstract_canon_sha256":"baaf1a3397c3c54da7332e26149514120e9a75beb25519211b21f77c962bc39a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:13.542794Z","signature_b64":"nfc4ot9pxkUg/1VbWo7WxomDnLxkgAaXg3DNcLbDM/RaG7Z9bxwTgJMicE4e+nhkKLVOaOh9LZV/i8m+QbUSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d6f44221a71e77a601acc3b6fdee59f35bd38a15e686995d04227e38b9d21da","last_reissued_at":"2026-07-05T05:07:13.542408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:13.542408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Woo Suk Choi, Yu-Jung Heo","submitted_at":"2022-10-17T00:37:00Z","abstract_excerpt":"Scene graph is structured semantic representation that can be modeled as a form of graph from images and texts. Image-based scene graph generation research has been actively conducted until recently, whereas text-based scene graph generation research has not. In this paper, we focus on the problem of scene graph parsing from textual description of a visual scene. The core idea is to use abstract meaning representation (AMR) instead of the dependency parsing mainly used in previous studies. AMR is a graph-based semantic formalism of natural language which abstracts concepts of words in a senten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08675","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/2210.08675/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.08675","created_at":"2026-07-05T05:07:13.542466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08675v1","created_at":"2026-07-05T05:07:13.542466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08675","created_at":"2026-07-05T05:07:13.542466+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVXUIIQ2OHTX","created_at":"2026-07-05T05:07:13.542466+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVXUIIQ2OHTXUYA2","created_at":"2026-07-05T05:07:13.542466+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVXUIIQ2","created_at":"2026-07-05T05:07:13.542466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12829","citing_title":"Human-Robot Dialogue Annotation for Multi-Modal Common Ground","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4","json":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4.json","graph_json":"https://pith.science/api/pith-number/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/graph.json","events_json":"https://pith.science/api/pith-number/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/events.json","paper":"https://pith.science/paper/RVXUIIQ2"},"agent_actions":{"view_html":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4","download_json":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4.json","view_paper":"https://pith.science/paper/RVXUIIQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08675&json=true","fetch_graph":"https://pith.science/api/pith-number/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/graph.json","fetch_events":"https://pith.science/api/pith-number/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/action/storage_attestation","attest_author":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/action/author_attestation","sign_citation":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/action/citation_signature","submit_replication":"https://pith.science/pith/RVXUIIQ2OHTXUYA2ZQ5W7XXFT4/action/replication_record"}},"created_at":"2026-07-05T05:07:13.542466+00:00","updated_at":"2026-07-05T05:07:13.542466+00:00"}