{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KKZ7LB3P6DJWVMDLEE6PIABJ5F","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":"4fda9ccce58bade8cf0d099b18dceb19b591c26cc7db76b28fb18ed6c9abb0e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-28T10:10:29Z","title_canon_sha256":"cdb48c5717423d4123e955a0dc9abcb39a81861dc1efd8b7d36950be83d37158"},"schema_version":"1.0","source":{"id":"2104.13682","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.13682","created_at":"2026-07-05T02:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2104.13682v1","created_at":"2026-07-05T02:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13682","created_at":"2026-07-05T02:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"KKZ7LB3P6DJW","created_at":"2026-07-05T02:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"KKZ7LB3P6DJWVMDL","created_at":"2026-07-05T02:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"KKZ7LB3P","created_at":"2026-07-05T02:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:7ca4721dd47b18efcd8b9707af59bb0a9d5ac8ba9fb79b54003c0b87b07e19e7","target":"graph","created_at":"2026-07-05T02:35:57Z","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/2104.13682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human-Object Interaction (HOI) detection is a task of identifying \"a set of interactions\" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels. Most existing methods have indirectly addressed this task by detecting human and object instances and individually inferring every pair of the detected instances. In this paper, we present a novel framework, referred to by HOTR, which directly predicts a set of <human, object, interaction> triplets from an image based on a transforme","authors_text":"Bumsoo Kim, Eun-Sol Kim, Hyunwoo J. Kim, Jaewoo Kang, Junhyun Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-28T10:10:29Z","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13682","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:acd0ff4918a7691592e17115130a3038b4d78ce5d8f39e0e5437fb69201be83c","target":"record","created_at":"2026-07-05T02:35:57Z","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":"4fda9ccce58bade8cf0d099b18dceb19b591c26cc7db76b28fb18ed6c9abb0e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-28T10:10:29Z","title_canon_sha256":"cdb48c5717423d4123e955a0dc9abcb39a81861dc1efd8b7d36950be83d37158"},"schema_version":"1.0","source":{"id":"2104.13682","kind":"arxiv","version":1}},"canonical_sha256":"52b3f5876ff0d36ab06b213cf40029e966fca5031c9bca23d1316b4796834b73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52b3f5876ff0d36ab06b213cf40029e966fca5031c9bca23d1316b4796834b73","first_computed_at":"2026-07-05T02:35:57.278749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:35:57.278749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0zpOiUtt18zWq+//ANPVWQpW2FMgvWPmShVubcS6D7Zg/QhxIjTthZ+4gtRYOSIfFT1lFND3fVO4c3l1EMq9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:35:57.279187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.13682","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acd0ff4918a7691592e17115130a3038b4d78ce5d8f39e0e5437fb69201be83c","sha256:7ca4721dd47b18efcd8b9707af59bb0a9d5ac8ba9fb79b54003c0b87b07e19e7"],"state_sha256":"aa5edfe55f6bd6eb202eebbc12f766c228fe624232f0c6e21ef1a02fc409bdef"}