{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:G364DHVXYYCTGMCOTX56GHZ6P6","short_pith_number":"pith:G364DHVX","schema_version":"1.0","canonical_sha256":"36fdc19eb7c60533304e9dfbe31f3e7fa1db387bb61898a1e0dc821da18c1f9c","source":{"kind":"arxiv","id":"1802.05451","version":4},"attestation_state":"computed","paper":{"title":"Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Amir Globerson, Gal Chechik, Jonathan Berant, Moshiko Raboh, Roei Herzig","submitted_at":"2018-02-15T09:50:15Z","abstract_excerpt":"Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing such effects is structured prediction, which optimizes over complex labels, while modeling within-label interactions. However, it is unclear what principles should guide the design of a structured prediction model that utilizes the power of deep learning components. Here we propose a design principle f"},"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":"1802.05451","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-15T09:50:15Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"9b54c27f163caedb9069569826ddb4156bf8032ada3ed8fe333a5e3d0bfde59f","abstract_canon_sha256":"b1109ec355121f6a6da68895975aed6f53ad1f43132dd1e357ebe55ee985b4fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:43.616160Z","signature_b64":"p1uak74LXK1luyIqO9MLFm0pPNfJkQXGU11ykbAKX4ENbzSqWuU9Y9sBOJenM5dJkwFSeADLyaUX97UhfwDPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36fdc19eb7c60533304e9dfbe31f3e7fa1db387bb61898a1e0dc821da18c1f9c","last_reissued_at":"2026-05-18T00:01:43.615743Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:43.615743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Amir Globerson, Gal Chechik, Jonathan Berant, Moshiko Raboh, Roei Herzig","submitted_at":"2018-02-15T09:50:15Z","abstract_excerpt":"Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing such effects is structured prediction, which optimizes over complex labels, while modeling within-label interactions. However, it is unclear what principles should guide the design of a structured prediction model that utilizes the power of deep learning components. Here we propose a design principle f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05451","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.05451","created_at":"2026-05-18T00:01:43.615812+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05451v4","created_at":"2026-05-18T00:01:43.615812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05451","created_at":"2026-05-18T00:01:43.615812+00:00"},{"alias_kind":"pith_short_12","alias_value":"G364DHVXYYCT","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"G364DHVXYYCTGMCO","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"G364DHVX","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6","json":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6.json","graph_json":"https://pith.science/api/pith-number/G364DHVXYYCTGMCOTX56GHZ6P6/graph.json","events_json":"https://pith.science/api/pith-number/G364DHVXYYCTGMCOTX56GHZ6P6/events.json","paper":"https://pith.science/paper/G364DHVX"},"agent_actions":{"view_html":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6","download_json":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6.json","view_paper":"https://pith.science/paper/G364DHVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05451&json=true","fetch_graph":"https://pith.science/api/pith-number/G364DHVXYYCTGMCOTX56GHZ6P6/graph.json","fetch_events":"https://pith.science/api/pith-number/G364DHVXYYCTGMCOTX56GHZ6P6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6/action/storage_attestation","attest_author":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6/action/author_attestation","sign_citation":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6/action/citation_signature","submit_replication":"https://pith.science/pith/G364DHVXYYCTGMCOTX56GHZ6P6/action/replication_record"}},"created_at":"2026-05-18T00:01:43.615812+00:00","updated_at":"2026-05-18T00:01:43.615812+00:00"}