{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AQURGUPKU7YJYD36LBNIINHOHD","short_pith_number":"pith:AQURGUPK","canonical_record":{"source":{"id":"2404.00906","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T04:21:01Z","cross_cats_sorted":[],"title_canon_sha256":"0b4520acbaba2f08188782a7f4d5e410d4b2c3b10abd6bbdc5e171ae7cc38c36","abstract_canon_sha256":"dbcd48d90a8fc008941953008d1e83ba3ca438fd0343028e1f4e2af1831e0317"},"schema_version":"1.0"},"canonical_sha256":"04291351eaa7f09c0f7e585a8434ee38f27e26859b86a7520e7762dafbf43387","source":{"kind":"arxiv","id":"2404.00906","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00906","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00906v3","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00906","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"AQURGUPKU7YJ","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"AQURGUPKU7YJYD36","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"AQURGUPK","created_at":"2026-07-05T08:11:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AQURGUPKU7YJYD36LBNIINHOHD","target":"record","payload":{"canonical_record":{"source":{"id":"2404.00906","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T04:21:01Z","cross_cats_sorted":[],"title_canon_sha256":"0b4520acbaba2f08188782a7f4d5e410d4b2c3b10abd6bbdc5e171ae7cc38c36","abstract_canon_sha256":"dbcd48d90a8fc008941953008d1e83ba3ca438fd0343028e1f4e2af1831e0317"},"schema_version":"1.0"},"canonical_sha256":"04291351eaa7f09c0f7e585a8434ee38f27e26859b86a7520e7762dafbf43387","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:23.859905Z","signature_b64":"OjGTZ8jBbd9kmaht/nqbZjiEMMDg9w1BbjvZ9dWMbdU6TT0cOb5kqJRommgp4hfmrxn4XHHysmBZDDh3KvvMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04291351eaa7f09c0f7e585a8434ee38f27e26859b86a7520e7762dafbf43387","last_reissued_at":"2026-07-05T08:11:23.859518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:23.859518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.00906","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qv0SLqDSNZfXvyEv9jxCYI6ZMPK3+FwgHdnQun9q9tubKBFKACsAGmUdezx4f/GBInnx4XNJLYLZS7/Lj1DSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:38:47.815267Z"},"content_sha256":"1d79a72aefbc9cdd7d289fa88909526ddb7068f896ebbbad5c98ab94804a4dfd","schema_version":"1.0","event_id":"sha256:1d79a72aefbc9cdd7d289fa88909526ddb7068f896ebbbad5c98ab94804a4dfd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AQURGUPKU7YJYD36LBNIINHOHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Kai Chen, Rongjie Li, Songyang Zhang, Xuming He","submitted_at":"2024-04-01T04:21:01Z","abstract_excerpt":"Scene graph generation (SGG) aims to parse a visual scene into an intermediate graph representation for downstream reasoning tasks. Despite recent advancements, existing methods struggle to generate scene graphs with novel visual relation concepts. To address this challenge, we introduce a new open-vocabulary SGG framework based on sequence generation. Our framework leverages vision-language pre-trained models (VLM) by incorporating an image-to-graph generation paradigm. Specifically, we generate scene graph sequences via image-to-text generation with VLM and then construct scene graphs from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00906","kind":"arxiv","version":3},"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/2404.00906/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":"2026-07-05T08:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dv1k+DP5u+8wIGjsLgnxR4p+12nQ7k05XTeldjKsbl4M4Uki9OTK2+2q3ygHrbyKX1yCqGYnLPpMa/1latQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:38:47.815863Z"},"content_sha256":"1cd228341bca65f3e6f37bad2449cf75f46170e7e2bccb796b10b9ebb63e8e61","schema_version":"1.0","event_id":"sha256:1cd228341bca65f3e6f37bad2449cf75f46170e7e2bccb796b10b9ebb63e8e61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQURGUPKU7YJYD36LBNIINHOHD/bundle.json","state_url":"https://pith.science/pith/AQURGUPKU7YJYD36LBNIINHOHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQURGUPKU7YJYD36LBNIINHOHD/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":"2026-08-10T13:38:47Z","links":{"resolver":"https://pith.science/pith/AQURGUPKU7YJYD36LBNIINHOHD","bundle":"https://pith.science/pith/AQURGUPKU7YJYD36LBNIINHOHD/bundle.json","state":"https://pith.science/pith/AQURGUPKU7YJYD36LBNIINHOHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQURGUPKU7YJYD36LBNIINHOHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AQURGUPKU7YJYD36LBNIINHOHD","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":"dbcd48d90a8fc008941953008d1e83ba3ca438fd0343028e1f4e2af1831e0317","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T04:21:01Z","title_canon_sha256":"0b4520acbaba2f08188782a7f4d5e410d4b2c3b10abd6bbdc5e171ae7cc38c36"},"schema_version":"1.0","source":{"id":"2404.00906","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00906","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00906v3","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00906","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"AQURGUPKU7YJ","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"AQURGUPKU7YJYD36","created_at":"2026-07-05T08:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"AQURGUPK","created_at":"2026-07-05T08:11:23Z"}],"graph_snapshots":[{"event_id":"sha256:1cd228341bca65f3e6f37bad2449cf75f46170e7e2bccb796b10b9ebb63e8e61","target":"graph","created_at":"2026-07-05T08:11:23Z","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/2404.00906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scene graph generation (SGG) aims to parse a visual scene into an intermediate graph representation for downstream reasoning tasks. Despite recent advancements, existing methods struggle to generate scene graphs with novel visual relation concepts. To address this challenge, we introduce a new open-vocabulary SGG framework based on sequence generation. Our framework leverages vision-language pre-trained models (VLM) by incorporating an image-to-graph generation paradigm. Specifically, we generate scene graph sequences via image-to-text generation with VLM and then construct scene graphs from t","authors_text":"Dahua Lin, Kai Chen, Rongjie Li, Songyang Zhang, Xuming He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T04:21:01Z","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00906","kind":"arxiv","version":3},"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":"sha256:1d79a72aefbc9cdd7d289fa88909526ddb7068f896ebbbad5c98ab94804a4dfd","target":"record","created_at":"2026-07-05T08:11:23Z","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":"dbcd48d90a8fc008941953008d1e83ba3ca438fd0343028e1f4e2af1831e0317","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T04:21:01Z","title_canon_sha256":"0b4520acbaba2f08188782a7f4d5e410d4b2c3b10abd6bbdc5e171ae7cc38c36"},"schema_version":"1.0","source":{"id":"2404.00906","kind":"arxiv","version":3}},"canonical_sha256":"04291351eaa7f09c0f7e585a8434ee38f27e26859b86a7520e7762dafbf43387","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04291351eaa7f09c0f7e585a8434ee38f27e26859b86a7520e7762dafbf43387","first_computed_at":"2026-07-05T08:11:23.859518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:23.859518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OjGTZ8jBbd9kmaht/nqbZjiEMMDg9w1BbjvZ9dWMbdU6TT0cOb5kqJRommgp4hfmrxn4XHHysmBZDDh3KvvMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:23.859905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00906","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d79a72aefbc9cdd7d289fa88909526ddb7068f896ebbbad5c98ab94804a4dfd","sha256:1cd228341bca65f3e6f37bad2449cf75f46170e7e2bccb796b10b9ebb63e8e61"],"state_sha256":"580756d714ed9c7df5345d3c6675a50e3ec371103997b4cae2db9a86c12dd17b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FgW2l2NyW/rje5FqUqjPtZPuwpZzDx/W3KpKrHrPRyrHAcK5RFPZrR6R3dNYrECdyGCF0sy4/DD+o1jPIRNfDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:38:47.822388Z","bundle_sha256":"c252da3e6cfcee9e4769f7f70fd0087a437d45f5132361d5a07ac2c36e483238"}}