{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NRN46TGMKVELBBUQPEPDB23REO","short_pith_number":"pith:NRN46TGM","canonical_record":{"source":{"id":"2507.06510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T03:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"5207c01baee22d9d3af25009a9cefc775a057f634ea758178a706474462bfdf1","abstract_canon_sha256":"adfc47429c72f3f0fa29a42b50900022ef2e01d9dc36b446c2dd7ae6db70726d"},"schema_version":"1.0"},"canonical_sha256":"6c5bcf4ccc5548b08690791e30eb71239816b8bb32e99e28f8bcacd609730d98","source":{"kind":"arxiv","id":"2507.06510","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06510","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06510v1","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06510","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"pith_short_12","alias_value":"NRN46TGMKVEL","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"pith_short_16","alias_value":"NRN46TGMKVELBBUQ","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"pith_short_8","alias_value":"NRN46TGM","created_at":"2026-07-05T11:34:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NRN46TGMKVELBBUQPEPDB23REO","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T03:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"5207c01baee22d9d3af25009a9cefc775a057f634ea758178a706474462bfdf1","abstract_canon_sha256":"adfc47429c72f3f0fa29a42b50900022ef2e01d9dc36b446c2dd7ae6db70726d"},"schema_version":"1.0"},"canonical_sha256":"6c5bcf4ccc5548b08690791e30eb71239816b8bb32e99e28f8bcacd609730d98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:17.446764Z","signature_b64":"Y5AMAef6TV5dH2GyIhUSSnZS1S6D5PKTY9ha3KLSN/doeQ1Cce08E5peqX8sJ0sR38kqLEC5b9EvrUnlEJaxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c5bcf4ccc5548b08690791e30eb71239816b8bb32e99e28f8bcacd609730d98","last_reissued_at":"2026-07-05T11:34:17.446335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:17.446335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06510","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":"2026-07-05T11:34:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kLl2wWmSc90d4WrMIdRAsZkcNQmt9VYC8nzHqLoWEkfFuEkUTY1q5k/gz78ORbGXixF5K3A9vRSX+0Nnl+tkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T05:59:41.719700Z"},"content_sha256":"5d02a71ba1ef48fec6f7de077fe15d096fe64459c31faee93feaa5d2b78ef698","schema_version":"1.0","event_id":"sha256:5d02a71ba1ef48fec6f7de077fe15d096fe64459c31faee93feaa5d2b78ef698"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NRN46TGMKVELBBUQPEPDB23REO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Sun, Changxing Ding, Shaoli Huang, Xiangmin Xu, Yupeng Hu","submitted_at":"2025-07-09T03:16:39Z","abstract_excerpt":"Open vocabulary Human-Object Interaction (HOI) detection is a challenging task that detects all <human, verb, object> triplets of interest in an image, even those that are not pre-defined in the training set. Existing approaches typically rely on output features generated by large Vision-Language Models (VLMs) to enhance the generalization ability of interaction representations. However, the visual features produced by VLMs are holistic and coarse-grained, which contradicts the nature of detection tasks. To address this issue, we propose a novel Bilateral Collaboration framework for open vocab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06510","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/2507.06510/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":"2026-07-05T11:34:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2GjHxrPeLtAfb43ULYbgLDBdYtU2n7mr/TXrXLMbP8wWmJr734+QRUAo7dlf6cdfPRqWdz1rL6CRH4smfeCZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T05:59:41.720259Z"},"content_sha256":"aa520de67f5da04cf9f14bb38f2b2cf3ce072d75e05710bc0c54f7e10c7fce5d","schema_version":"1.0","event_id":"sha256:aa520de67f5da04cf9f14bb38f2b2cf3ce072d75e05710bc0c54f7e10c7fce5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/bundle.json","state_url":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRN46TGMKVELBBUQPEPDB23REO/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":"2026-08-20T05:59:41Z","links":{"resolver":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO","bundle":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/bundle.json","state":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRN46TGMKVELBBUQPEPDB23REO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NRN46TGMKVELBBUQPEPDB23REO","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":"adfc47429c72f3f0fa29a42b50900022ef2e01d9dc36b446c2dd7ae6db70726d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T03:16:39Z","title_canon_sha256":"5207c01baee22d9d3af25009a9cefc775a057f634ea758178a706474462bfdf1"},"schema_version":"1.0","source":{"id":"2507.06510","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06510","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06510v1","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06510","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"pith_short_12","alias_value":"NRN46TGMKVEL","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"pith_short_16","alias_value":"NRN46TGMKVELBBUQ","created_at":"2026-07-05T11:34:17Z"},{"alias_kind":"pith_short_8","alias_value":"NRN46TGM","created_at":"2026-07-05T11:34:17Z"}],"graph_snapshots":[{"event_id":"sha256:aa520de67f5da04cf9f14bb38f2b2cf3ce072d75e05710bc0c54f7e10c7fce5d","target":"graph","created_at":"2026-07-05T11:34:17Z","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/2507.06510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open vocabulary Human-Object Interaction (HOI) detection is a challenging task that detects all <human, verb, object> triplets of interest in an image, even those that are not pre-defined in the training set. Existing approaches typically rely on output features generated by large Vision-Language Models (VLMs) to enhance the generalization ability of interaction representations. However, the visual features produced by VLMs are holistic and coarse-grained, which contradicts the nature of detection tasks. To address this issue, we propose a novel Bilateral Collaboration framework for open vocab","authors_text":"Chang Sun, Changxing Ding, Shaoli Huang, Xiangmin Xu, Yupeng Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T03:16:39Z","title":"Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06510","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":"sha256:5d02a71ba1ef48fec6f7de077fe15d096fe64459c31faee93feaa5d2b78ef698","target":"record","created_at":"2026-07-05T11:34:17Z","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":"adfc47429c72f3f0fa29a42b50900022ef2e01d9dc36b446c2dd7ae6db70726d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T03:16:39Z","title_canon_sha256":"5207c01baee22d9d3af25009a9cefc775a057f634ea758178a706474462bfdf1"},"schema_version":"1.0","source":{"id":"2507.06510","kind":"arxiv","version":1}},"canonical_sha256":"6c5bcf4ccc5548b08690791e30eb71239816b8bb32e99e28f8bcacd609730d98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c5bcf4ccc5548b08690791e30eb71239816b8bb32e99e28f8bcacd609730d98","first_computed_at":"2026-07-05T11:34:17.446335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:17.446335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y5AMAef6TV5dH2GyIhUSSnZS1S6D5PKTY9ha3KLSN/doeQ1Cce08E5peqX8sJ0sR38kqLEC5b9EvrUnlEJaxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:17.446764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06510","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d02a71ba1ef48fec6f7de077fe15d096fe64459c31faee93feaa5d2b78ef698","sha256:aa520de67f5da04cf9f14bb38f2b2cf3ce072d75e05710bc0c54f7e10c7fce5d"],"state_sha256":"dab5e7dbedbf8cbf7c586aced159fae7eb7b05075a571ff5f87e3681a337393c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6CdsOIZUX7UDOxAwERj+MV+AkDYqTiiNuNfh3YMY+4a1ez/pzHEX/B4DyV4FLVDOvShfrBVmoq1SJEXpFiiAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T05:59:41.726765Z","bundle_sha256":"eac2b3133b62c3ae25229a7aa87817932695307b5a3af9f0f749d7bd27575278"}}