{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7GRQVU4ANERCZXDYYRF25AZK6H","short_pith_number":"pith:7GRQVU4A","canonical_record":{"source":{"id":"2506.05651","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T00:43:15Z","cross_cats_sorted":[],"title_canon_sha256":"1ebb29e86bd5c95cbcd6cbc96dea7f82490e096fe97f224c59fcd45910fb0c5c","abstract_canon_sha256":"99872efa05541dec044f99f01a6e115bda074d72ebbda49082cd9841de2a5620"},"schema_version":"1.0"},"canonical_sha256":"f9a30ad38069222cdc78c44bae832af1d37cd58930f4be77f78d78787e181690","source":{"kind":"arxiv","id":"2506.05651","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05651","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05651v1","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05651","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_12","alias_value":"7GRQVU4ANERC","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_16","alias_value":"7GRQVU4ANERCZXDY","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_8","alias_value":"7GRQVU4A","created_at":"2026-07-05T11:17:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7GRQVU4ANERCZXDYYRF25AZK6H","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05651","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T00:43:15Z","cross_cats_sorted":[],"title_canon_sha256":"1ebb29e86bd5c95cbcd6cbc96dea7f82490e096fe97f224c59fcd45910fb0c5c","abstract_canon_sha256":"99872efa05541dec044f99f01a6e115bda074d72ebbda49082cd9841de2a5620"},"schema_version":"1.0"},"canonical_sha256":"f9a30ad38069222cdc78c44bae832af1d37cd58930f4be77f78d78787e181690","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:07.561483Z","signature_b64":"pGCTNlHxVO/o7llJUKtOb/oKPYnDghA2tsGdMvpTsRB4FAWHnGn/W2sq1Hurh7ghTcE1AYdLn0x8teJJE0CCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9a30ad38069222cdc78c44bae832af1d37cd58930f4be77f78d78787e181690","last_reissued_at":"2026-07-05T11:17:07.560994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:07.560994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05651","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R1+nYFOi/1SQHl8pODNFxjLhqJgTkO+eK4lMhaaBJWTZjQ1WU8DjMdmxGq1HUxN6H6i3grtEKRm+f6GvSB5XDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:00:47.478215Z"},"content_sha256":"24f4f8f0fb3eb68af11aac8d7267c3d027e33ec0304e30aea06d484e7c3112df","schema_version":"1.0","event_id":"sha256:24f4f8f0fb3eb68af11aac8d7267c3d027e33ec0304e30aea06d484e7c3112df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7GRQVU4ANERCZXDYYRF25AZK6H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hallucinate, Ground, Repeat: A Framework for Generalized Visual Relationship Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Sanjoy Kundu, Sathyanarayanan N. Aakur, Shanmukha Vellamcheti","submitted_at":"2025-06-06T00:43:15Z","abstract_excerpt":"Understanding relationships between objects is central to visual intelligence, with applications in embodied AI, assistive systems, and scene understanding. Yet, most visual relationship detection (VRD) models rely on a fixed predicate set, limiting their generalization to novel interactions. A key challenge is the inability to visually ground semantically plausible, but unannotated, relationships hypothesized from external knowledge. This work introduces an iterative visual grounding framework that leverages large language models (LLMs) as structured relational priors. Inspired by expectation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05651","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/2506.05651/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":"2026-07-05T11:17:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DpWIJz3oRccDsIjX9mrctpcG20dplEvd9x3eMYP+a36E3NKehIVxrXYmd7uHUwBJIvG3v7MtGk39uJvH/4s4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:00:47.478739Z"},"content_sha256":"494c3e0424fd801d05fdb56b34fb33e8f300eaf27fe292058741efc1b597d99c","schema_version":"1.0","event_id":"sha256:494c3e0424fd801d05fdb56b34fb33e8f300eaf27fe292058741efc1b597d99c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GRQVU4ANERCZXDYYRF25AZK6H/bundle.json","state_url":"https://pith.science/pith/7GRQVU4ANERCZXDYYRF25AZK6H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GRQVU4ANERCZXDYYRF25AZK6H/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":"2026-08-07T21:00:47Z","links":{"resolver":"https://pith.science/pith/7GRQVU4ANERCZXDYYRF25AZK6H","bundle":"https://pith.science/pith/7GRQVU4ANERCZXDYYRF25AZK6H/bundle.json","state":"https://pith.science/pith/7GRQVU4ANERCZXDYYRF25AZK6H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GRQVU4ANERCZXDYYRF25AZK6H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7GRQVU4ANERCZXDYYRF25AZK6H","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":"99872efa05541dec044f99f01a6e115bda074d72ebbda49082cd9841de2a5620","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T00:43:15Z","title_canon_sha256":"1ebb29e86bd5c95cbcd6cbc96dea7f82490e096fe97f224c59fcd45910fb0c5c"},"schema_version":"1.0","source":{"id":"2506.05651","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05651","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05651v1","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05651","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_12","alias_value":"7GRQVU4ANERC","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_16","alias_value":"7GRQVU4ANERCZXDY","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_8","alias_value":"7GRQVU4A","created_at":"2026-07-05T11:17:07Z"}],"graph_snapshots":[{"event_id":"sha256:494c3e0424fd801d05fdb56b34fb33e8f300eaf27fe292058741efc1b597d99c","target":"graph","created_at":"2026-07-05T11:17:07Z","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/2506.05651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding relationships between objects is central to visual intelligence, with applications in embodied AI, assistive systems, and scene understanding. Yet, most visual relationship detection (VRD) models rely on a fixed predicate set, limiting their generalization to novel interactions. A key challenge is the inability to visually ground semantically plausible, but unannotated, relationships hypothesized from external knowledge. This work introduces an iterative visual grounding framework that leverages large language models (LLMs) as structured relational priors. Inspired by expectation","authors_text":"Sanjoy Kundu, Sathyanarayanan N. Aakur, Shanmukha Vellamcheti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T00:43:15Z","title":"Hallucinate, Ground, Repeat: A Framework for Generalized Visual Relationship Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05651","kind":"arxiv","version":1},"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":"sha256:24f4f8f0fb3eb68af11aac8d7267c3d027e33ec0304e30aea06d484e7c3112df","target":"record","created_at":"2026-07-05T11:17:07Z","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":"99872efa05541dec044f99f01a6e115bda074d72ebbda49082cd9841de2a5620","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T00:43:15Z","title_canon_sha256":"1ebb29e86bd5c95cbcd6cbc96dea7f82490e096fe97f224c59fcd45910fb0c5c"},"schema_version":"1.0","source":{"id":"2506.05651","kind":"arxiv","version":1}},"canonical_sha256":"f9a30ad38069222cdc78c44bae832af1d37cd58930f4be77f78d78787e181690","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9a30ad38069222cdc78c44bae832af1d37cd58930f4be77f78d78787e181690","first_computed_at":"2026-07-05T11:17:07.560994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:07.560994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pGCTNlHxVO/o7llJUKtOb/oKPYnDghA2tsGdMvpTsRB4FAWHnGn/W2sq1Hurh7ghTcE1AYdLn0x8teJJE0CCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:07.561483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05651","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24f4f8f0fb3eb68af11aac8d7267c3d027e33ec0304e30aea06d484e7c3112df","sha256:494c3e0424fd801d05fdb56b34fb33e8f300eaf27fe292058741efc1b597d99c"],"state_sha256":"53e1200184a2176b8f8ce1ca07714930a08c79e1b421a9438b75096938a35d79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zWjAVUiL1meD8vsjOejAW7zh+faHMTMpQV/I7ttqlrZVcJCmpeDEAWZGHeRKjMBEgnWO6xB1iVpOEG7AsivPDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:00:47.483917Z","bundle_sha256":"a5152de6a8a83962b8704b3a598052e93d9f9b36e3f2f5a4d43a4fad8335618d"}}