{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6SAGDOANOMYDIIHPPNVL5EVNQS","short_pith_number":"pith:6SAGDOAN","canonical_record":{"source":{"id":"2403.14270","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:15:57Z","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"bb2d169199dbb281d234cda47111a095fbc8ed9233802f016500bed9a0b25148","abstract_canon_sha256":"5f0c1806c32346518e98bd559e301ff33f0679412fdb66ceffb62017da6d87df"},"schema_version":"1.0"},"canonical_sha256":"f48061b80d73303420ef7b6abe92ad849c6dd49bb04803a2c113c8311f2d2b93","source":{"kind":"arxiv","id":"2403.14270","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14270","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14270v2","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14270","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"6SAGDOANOMYD","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"6SAGDOANOMYDIIHP","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"6SAGDOAN","created_at":"2026-07-05T08:46:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6SAGDOANOMYDIIHPPNVL5EVNQS","target":"record","payload":{"canonical_record":{"source":{"id":"2403.14270","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:15:57Z","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"bb2d169199dbb281d234cda47111a095fbc8ed9233802f016500bed9a0b25148","abstract_canon_sha256":"5f0c1806c32346518e98bd559e301ff33f0679412fdb66ceffb62017da6d87df"},"schema_version":"1.0"},"canonical_sha256":"f48061b80d73303420ef7b6abe92ad849c6dd49bb04803a2c113c8311f2d2b93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:07.585911Z","signature_b64":"u5kSRd0cmHhquf2LfEwF8PRjaemwJgCzRzSAh3yVOf5NoflnrjQk/4MfBZ4qLkJvxSL58s5c2+2jERkmlVLQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f48061b80d73303420ef7b6abe92ad849c6dd49bb04803a2c113c8311f2d2b93","last_reissued_at":"2026-07-05T08:46:07.585361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:07.585361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.14270","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":"2026-07-05T08:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W6XvOYoh//gqoQdUHgeXXUYsD74rvRX3YW89kRSECFyc8Vz28gjjProlPhF1rOkbJYQ9xWWqkHxXjuYUrlSXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:47:01.705491Z"},"content_sha256":"e70416fa76a5b0b00d6fbec07f74609041403d92530f5718c0f6f6a9f2f933da","schema_version":"1.0","event_id":"sha256:e70416fa76a5b0b00d6fbec07f74609041403d92530f5718c0f6f6a9f2f933da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6SAGDOANOMYDIIHPPNVL5EVNQS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alex Bewley, Markus Ryll, Matthias Minderer, Tim Salzmann","submitted_at":"2024-03-21T10:15:57Z","abstract_excerpt":"Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach this task by adding separate relationship modules or decoders to existing object detection architectures. This separation increases complexity and hinders end-to-end training, which limits performance. We propose a simple and highly efficient decoder-free architecture for open-vocabulary visual relationship detection. Our model consists of a Transformer-based image encoder that represents objects as tokens and models their relationships implicitly. To extract relationship informatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14270","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/2403.14270/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":"2026-07-05T08:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"umO5hcCdHUvC2smU5TuprfYTbcdUMcxuns2MXDoYcUhhW03kOTD/tBWg08PrXle+4qubz/Rq8Vx8tA9imEd0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:47:01.705901Z"},"content_sha256":"712f3c13d65e4cab9fe49770a3d16a485e5a997653f1601aced4ba36852b2b4c","schema_version":"1.0","event_id":"sha256:712f3c13d65e4cab9fe49770a3d16a485e5a997653f1601aced4ba36852b2b4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SAGDOANOMYDIIHPPNVL5EVNQS/bundle.json","state_url":"https://pith.science/pith/6SAGDOANOMYDIIHPPNVL5EVNQS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SAGDOANOMYDIIHPPNVL5EVNQS/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":"2026-07-08T07:47:01Z","links":{"resolver":"https://pith.science/pith/6SAGDOANOMYDIIHPPNVL5EVNQS","bundle":"https://pith.science/pith/6SAGDOANOMYDIIHPPNVL5EVNQS/bundle.json","state":"https://pith.science/pith/6SAGDOANOMYDIIHPPNVL5EVNQS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SAGDOANOMYDIIHPPNVL5EVNQS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6SAGDOANOMYDIIHPPNVL5EVNQS","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":"5f0c1806c32346518e98bd559e301ff33f0679412fdb66ceffb62017da6d87df","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:15:57Z","title_canon_sha256":"bb2d169199dbb281d234cda47111a095fbc8ed9233802f016500bed9a0b25148"},"schema_version":"1.0","source":{"id":"2403.14270","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14270","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14270v2","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14270","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"6SAGDOANOMYD","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"6SAGDOANOMYDIIHP","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"6SAGDOAN","created_at":"2026-07-05T08:46:07Z"}],"graph_snapshots":[{"event_id":"sha256:712f3c13d65e4cab9fe49770a3d16a485e5a997653f1601aced4ba36852b2b4c","target":"graph","created_at":"2026-07-05T08:46:07Z","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/2403.14270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach this task by adding separate relationship modules or decoders to existing object detection architectures. This separation increases complexity and hinders end-to-end training, which limits performance. We propose a simple and highly efficient decoder-free architecture for open-vocabulary visual relationship detection. Our model consists of a Transformer-based image encoder that represents objects as tokens and models their relationships implicitly. To extract relationship informatio","authors_text":"Alex Bewley, Markus Ryll, Matthias Minderer, Tim Salzmann","cross_cats":["cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:15:57Z","title":"Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14270","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:e70416fa76a5b0b00d6fbec07f74609041403d92530f5718c0f6f6a9f2f933da","target":"record","created_at":"2026-07-05T08:46:07Z","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":"5f0c1806c32346518e98bd559e301ff33f0679412fdb66ceffb62017da6d87df","cross_cats_sorted":["cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:15:57Z","title_canon_sha256":"bb2d169199dbb281d234cda47111a095fbc8ed9233802f016500bed9a0b25148"},"schema_version":"1.0","source":{"id":"2403.14270","kind":"arxiv","version":2}},"canonical_sha256":"f48061b80d73303420ef7b6abe92ad849c6dd49bb04803a2c113c8311f2d2b93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f48061b80d73303420ef7b6abe92ad849c6dd49bb04803a2c113c8311f2d2b93","first_computed_at":"2026-07-05T08:46:07.585361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:07.585361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5kSRd0cmHhquf2LfEwF8PRjaemwJgCzRzSAh3yVOf5NoflnrjQk/4MfBZ4qLkJvxSL58s5c2+2jERkmlVLQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:07.585911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14270","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e70416fa76a5b0b00d6fbec07f74609041403d92530f5718c0f6f6a9f2f933da","sha256:712f3c13d65e4cab9fe49770a3d16a485e5a997653f1601aced4ba36852b2b4c"],"state_sha256":"ae674d6206e9f2a64c9819734b4355eefad32e917da085e79f977ab719dbe8d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aU+VlPHexgJMbUl1O+Z3rCYqpUFiWneAeA1iiYQz4sQTSc8yXPS8JQ7f08i8posL9dzbPu+ZS9EZIVu4bysUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:47:01.708801Z","bundle_sha256":"7f553e3f374c83ad027dde10c6e440035d65ac5c67d669396690254e0b6f9c84"}}