{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DAUISZRUILI35FI3TUPYFRTIIK","short_pith_number":"pith:DAUISZRU","canonical_record":{"source":{"id":"2004.06193","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T20:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"90972d4cd7a42bd1690f560d0c7420dc9d5644ba889c128e95929911bdfe7542","abstract_canon_sha256":"9a104015c77f0baf022f4157c2fd0e6f11f3643425b9d5b28ca1c8f61d15a8c6"},"schema_version":"1.0"},"canonical_sha256":"182889663442d1be951b9d1f82c66842a4464194d4283bdd69728fae64ab19fd","source":{"kind":"arxiv","id":"2004.06193","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.06193","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"2004.06193v2","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06193","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"DAUISZRUILI3","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"DAUISZRUILI35FI3","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"DAUISZRU","created_at":"2026-07-05T02:59:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DAUISZRUILI35FI3TUPYFRTIIK","target":"record","payload":{"canonical_record":{"source":{"id":"2004.06193","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T20:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"90972d4cd7a42bd1690f560d0c7420dc9d5644ba889c128e95929911bdfe7542","abstract_canon_sha256":"9a104015c77f0baf022f4157c2fd0e6f11f3643425b9d5b28ca1c8f61d15a8c6"},"schema_version":"1.0"},"canonical_sha256":"182889663442d1be951b9d1f82c66842a4464194d4283bdd69728fae64ab19fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:34.721108Z","signature_b64":"Jjahx4ygfpL+QWgOLr9azmkrk4nxZ3YHV6tf+K8eCxZjuRqhpevIKl7AqvES4kgnYCOQEvMIpGoH9CZLWnWkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"182889663442d1be951b9d1f82c66842a4464194d4283bdd69728fae64ab19fd","last_reissued_at":"2026-07-05T02:59:34.720727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:34.720727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.06193","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSzHPxyq9x/HlF8MBCEmjbvCNBejkbB74f9wPqrsJvPb/wOq0wCj5BxcuMFBSi+Hp2L1dXPWDu/16jYvvgN4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:27:18.374257Z"},"content_sha256":"6015413df5b9b8b8aa594b7c2c5763771e30738c1339917a21db8ad75da2be12","schema_version":"1.0","event_id":"sha256:6015413df5b9b8b8aa594b7c2c5763771e30738c1339917a21db8ad75da2be12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DAUISZRUILI35FI3TUPYFRTIIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relation Transformer Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rajat Koner, Suprosanna Shit, Volker Tresp","submitted_at":"2020-04-13T20:47:01Z","abstract_excerpt":"The extraction of a scene graph with objects as nodes and mutual relationships as edges is the basis for a deep understanding of image content. Despite recent advances, such as message passing and joint classification, the detection of visual relationships remains a challenging task due to sub-optimal exploration of the mutual interaction among the visual objects. In this work, we propose a novel transformer formulation for scene graph generation and relation prediction. We leverage the encoder-decoder architecture of the transformer for rich feature embedding of nodes and edges. Specifically,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06193","kind":"arxiv","version":2},"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/2004.06193/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":"2026-07-05T02:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1GQqjaoN6rjT25b6xomodRKDi/f6l+svCgPU9p9DbQ0bmxSohxPACUItcMVcLM1fky+Of/5fDeEwMi0rPGsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:27:18.374773Z"},"content_sha256":"37ac1e58807b2aa7a78a142e66c8680e0eea4c035404dac4192b8ed76960050c","schema_version":"1.0","event_id":"sha256:37ac1e58807b2aa7a78a142e66c8680e0eea4c035404dac4192b8ed76960050c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/bundle.json","state_url":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAUISZRUILI35FI3TUPYFRTIIK/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":"2026-08-04T21:27:18Z","links":{"resolver":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK","bundle":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/bundle.json","state":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAUISZRUILI35FI3TUPYFRTIIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DAUISZRUILI35FI3TUPYFRTIIK","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":"9a104015c77f0baf022f4157c2fd0e6f11f3643425b9d5b28ca1c8f61d15a8c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T20:47:01Z","title_canon_sha256":"90972d4cd7a42bd1690f560d0c7420dc9d5644ba889c128e95929911bdfe7542"},"schema_version":"1.0","source":{"id":"2004.06193","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.06193","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"2004.06193v2","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06193","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"DAUISZRUILI3","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"DAUISZRUILI35FI3","created_at":"2026-07-05T02:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"DAUISZRU","created_at":"2026-07-05T02:59:34Z"}],"graph_snapshots":[{"event_id":"sha256:37ac1e58807b2aa7a78a142e66c8680e0eea4c035404dac4192b8ed76960050c","target":"graph","created_at":"2026-07-05T02:59:34Z","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/2004.06193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The extraction of a scene graph with objects as nodes and mutual relationships as edges is the basis for a deep understanding of image content. Despite recent advances, such as message passing and joint classification, the detection of visual relationships remains a challenging task due to sub-optimal exploration of the mutual interaction among the visual objects. In this work, we propose a novel transformer formulation for scene graph generation and relation prediction. We leverage the encoder-decoder architecture of the transformer for rich feature embedding of nodes and edges. Specifically,","authors_text":"Rajat Koner, Suprosanna Shit, Volker Tresp","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T20:47:01Z","title":"Relation Transformer Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06193","kind":"arxiv","version":2},"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":"sha256:6015413df5b9b8b8aa594b7c2c5763771e30738c1339917a21db8ad75da2be12","target":"record","created_at":"2026-07-05T02:59:34Z","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":"9a104015c77f0baf022f4157c2fd0e6f11f3643425b9d5b28ca1c8f61d15a8c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T20:47:01Z","title_canon_sha256":"90972d4cd7a42bd1690f560d0c7420dc9d5644ba889c128e95929911bdfe7542"},"schema_version":"1.0","source":{"id":"2004.06193","kind":"arxiv","version":2}},"canonical_sha256":"182889663442d1be951b9d1f82c66842a4464194d4283bdd69728fae64ab19fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"182889663442d1be951b9d1f82c66842a4464194d4283bdd69728fae64ab19fd","first_computed_at":"2026-07-05T02:59:34.720727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:34.720727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jjahx4ygfpL+QWgOLr9azmkrk4nxZ3YHV6tf+K8eCxZjuRqhpevIKl7AqvES4kgnYCOQEvMIpGoH9CZLWnWkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:34.721108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.06193","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6015413df5b9b8b8aa594b7c2c5763771e30738c1339917a21db8ad75da2be12","sha256:37ac1e58807b2aa7a78a142e66c8680e0eea4c035404dac4192b8ed76960050c"],"state_sha256":"b916be32d1861d5a2b4ecfc1580fdc5e5c3bd6839cff439cdec67490e43f7c4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7/HkzYewLTYxJplK32erc9BemKipqgz7DmehWlIHkBD8edD+qehI/SAOouh4mUkRhZE1Hn9L/V41AKauoYn5Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:27:18.381108Z","bundle_sha256":"6e1c154f6d4d62f1f8d311f33d5ce98cc7b7c8747c556e08c8c0717fc0d920fb"}}