{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KYGQJYA3PMBXBEQUZ6KKB74ZV7","short_pith_number":"pith:KYGQJYA3","canonical_record":{"source":{"id":"2505.19503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T04:31:34Z","cross_cats_sorted":[],"title_canon_sha256":"8d2c078054b4c37c991566bd3370136cb5ef4953943f89136325b3ee813ab0ea","abstract_canon_sha256":"2ee03c4a1c5abc6e5c7d06a854b0e7a185e6a8e26bda9f72a817c834e83f133d"},"schema_version":"1.0"},"canonical_sha256":"560d04e01b7b03709214cf94a0ff99afed57f1561491d83eb012c95b7375c7ae","source":{"kind":"arxiv","id":"2505.19503","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19503","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19503v1","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19503","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"KYGQJYA3PMBX","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"KYGQJYA3PMBXBEQU","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"KYGQJYA3","created_at":"2026-07-05T11:09:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KYGQJYA3PMBXBEQUZ6KKB74ZV7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T04:31:34Z","cross_cats_sorted":[],"title_canon_sha256":"8d2c078054b4c37c991566bd3370136cb5ef4953943f89136325b3ee813ab0ea","abstract_canon_sha256":"2ee03c4a1c5abc6e5c7d06a854b0e7a185e6a8e26bda9f72a817c834e83f133d"},"schema_version":"1.0"},"canonical_sha256":"560d04e01b7b03709214cf94a0ff99afed57f1561491d83eb012c95b7375c7ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:31.367266Z","signature_b64":"xu1qE3cHv79CVZD20zzbvw8D9mQNpZk6UpwM0O2jxBv+pINn6Lzd4HmiWGLMZzIX9tiy6ueJPYehJgacugo9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"560d04e01b7b03709214cf94a0ff99afed57f1561491d83eb012c95b7375c7ae","last_reissued_at":"2026-07-05T11:09:31.366746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:31.366746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19503","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":"2026-07-05T11:09:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8YmP7Tl7+iyz0ZMW6oMHO8+a4y4tB0x8yOv5gljeWbeYzQZklCDyEPcnMNB+1aO77jmhI/OEl5zs2ABPNi0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:01:16.077307Z"},"content_sha256":"7eca0fae24b988c876475194489f35d1192165fee040a5dfdd88bc338b37e461","schema_version":"1.0","event_id":"sha256:7eca0fae24b988c876475194489f35d1192165fee040a5dfdd88bc338b37e461"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KYGQJYA3PMBXBEQUZ6KKB74ZV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Locality-Aware Zero-Shot Human-Object Interaction Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deunsol Jung, Minsu Cho, Sanghyun Kim","submitted_at":"2025-05-26T04:31:34Z","abstract_excerpt":"Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot settings. However, existing methods struggle to adapt CLIP representations for human-object pairs, as CLIP tends to overlook fine-grained information necessary for distinguishing interactions. To address this issue, we devise, LAIN, a novel zero-shot HOI detection framework enhancing the locality and interaction awareness of CLIP representations. The locality aw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19503","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/2505.19503/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":"2026-07-05T11:09:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iF+ZioYa5R3EqmxKOR+3lbKreOY21Rm97fGvtPOIyRBINLuj1B/AKP+yTyy38jOxJnkQTTJLHEDtCnOIsILvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:01:16.077835Z"},"content_sha256":"33044ef6d166ae2f50ede387bfe6be64136a13911eba233626e3cd230db3024c","schema_version":"1.0","event_id":"sha256:33044ef6d166ae2f50ede387bfe6be64136a13911eba233626e3cd230db3024c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/bundle.json","state_url":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/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":"2026-08-08T21:01:16Z","links":{"resolver":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7","bundle":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/bundle.json","state":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KYGQJYA3PMBXBEQUZ6KKB74ZV7","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":"2ee03c4a1c5abc6e5c7d06a854b0e7a185e6a8e26bda9f72a817c834e83f133d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T04:31:34Z","title_canon_sha256":"8d2c078054b4c37c991566bd3370136cb5ef4953943f89136325b3ee813ab0ea"},"schema_version":"1.0","source":{"id":"2505.19503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19503","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19503v1","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19503","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"KYGQJYA3PMBX","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"KYGQJYA3PMBXBEQU","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"KYGQJYA3","created_at":"2026-07-05T11:09:31Z"}],"graph_snapshots":[{"event_id":"sha256:33044ef6d166ae2f50ede387bfe6be64136a13911eba233626e3cd230db3024c","target":"graph","created_at":"2026-07-05T11:09:31Z","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/2505.19503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot settings. However, existing methods struggle to adapt CLIP representations for human-object pairs, as CLIP tends to overlook fine-grained information necessary for distinguishing interactions. To address this issue, we devise, LAIN, a novel zero-shot HOI detection framework enhancing the locality and interaction awareness of CLIP representations. The locality aw","authors_text":"Deunsol Jung, Minsu Cho, Sanghyun Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T04:31:34Z","title":"Locality-Aware Zero-Shot Human-Object Interaction Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19503","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":"sha256:7eca0fae24b988c876475194489f35d1192165fee040a5dfdd88bc338b37e461","target":"record","created_at":"2026-07-05T11:09:31Z","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":"2ee03c4a1c5abc6e5c7d06a854b0e7a185e6a8e26bda9f72a817c834e83f133d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T04:31:34Z","title_canon_sha256":"8d2c078054b4c37c991566bd3370136cb5ef4953943f89136325b3ee813ab0ea"},"schema_version":"1.0","source":{"id":"2505.19503","kind":"arxiv","version":1}},"canonical_sha256":"560d04e01b7b03709214cf94a0ff99afed57f1561491d83eb012c95b7375c7ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"560d04e01b7b03709214cf94a0ff99afed57f1561491d83eb012c95b7375c7ae","first_computed_at":"2026-07-05T11:09:31.366746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:31.366746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xu1qE3cHv79CVZD20zzbvw8D9mQNpZk6UpwM0O2jxBv+pINn6Lzd4HmiWGLMZzIX9tiy6ueJPYehJgacugo9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:31.367266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eca0fae24b988c876475194489f35d1192165fee040a5dfdd88bc338b37e461","sha256:33044ef6d166ae2f50ede387bfe6be64136a13911eba233626e3cd230db3024c"],"state_sha256":"680ca7e1bc5bedb013ac48f9ca3fdc20b428d4a6548d01e339eec93bd8f8c85b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQZ4L64ZntKgYAVn7CT8XyrcOLrbQuRmlm29KIXN2A/X9XroxFNjSHR5uxfnDbNoVam8zeyHDBgLuTJUZ2HGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:01:16.081456Z","bundle_sha256":"d8d57a321d00c17f3ddddd93ecff55b9df0ec7d17d5c37cfa2b3b640f1812469"}}