{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4PH2U7EJ5TS5WAGLAZ4SZDX4KG","short_pith_number":"pith:4PH2U7EJ","canonical_record":{"source":{"id":"2605.05057","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T15:52:35Z","cross_cats_sorted":[],"title_canon_sha256":"5ba83a70b6539342e3fa653a8d3464a206d40a03beaee8e71d5a75b31d7aef91","abstract_canon_sha256":"ae304ecf7f00f4789847681c0eddaf2c8bfae8916d17565ba5f3950676dc8644"},"schema_version":"1.0"},"canonical_sha256":"e3cfaa7c89ece5db00cb06792c8efc5180aded54535774509e9f54a89bf8998a","source":{"kind":"arxiv","id":"2605.05057","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05057","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05057v3","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05057","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"4PH2U7EJ5TS5","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"4PH2U7EJ5TS5WAGL","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"4PH2U7EJ","created_at":"2026-05-27T01:04:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4PH2U7EJ5TS5WAGLAZ4SZDX4KG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.05057","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T15:52:35Z","cross_cats_sorted":[],"title_canon_sha256":"5ba83a70b6539342e3fa653a8d3464a206d40a03beaee8e71d5a75b31d7aef91","abstract_canon_sha256":"ae304ecf7f00f4789847681c0eddaf2c8bfae8916d17565ba5f3950676dc8644"},"schema_version":"1.0"},"canonical_sha256":"e3cfaa7c89ece5db00cb06792c8efc5180aded54535774509e9f54a89bf8998a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:58.800249Z","signature_b64":"oK9z3rgM2+qImeefjnFRL6zmBFVuCbNrbU+OIxFnLvgb2+30cmjAZr4cjFQP58gi8mn05zePCobnxptqadGQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3cfaa7c89ece5db00cb06792c8efc5180aded54535774509e9f54a89bf8998a","last_reissued_at":"2026-05-27T01:04:58.799764Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:58.799764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.05057","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":"2026-05-27T01:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I2Tev3sD7P08D7IfDDbCgO5k0TmkJH41bfpV9pwxDgAJchCXpaQWv1uUfW4vx8ymtbSU8AOwY4Up7yge6t6UDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:32:04.275881Z"},"content_sha256":"7557803e97692d38d7d93d4a0996cc4c9629ae7d7c7648effc30fb45cc0a7ccc","schema_version":"1.0","event_id":"sha256:7557803e97692d38d7d93d4a0996cc4c9629ae7d7c7648effc30fb45cc0a7ccc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4PH2U7EJ5TS5WAGLAZ4SZDX4KG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Decomposing interaction phrases into state slots verifies multiple visual cues and improves rare and unseen human-object interaction detection.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bao Ngoc Le, Linh Chi Vo, Minh Anh Nguyen, Quang Huy Tran, Suiyang Guang, Tuan Kiet Pham","submitted_at":"2026-05-06T15:52:35Z","abstract_excerpt":"Open-vocabulary human-object interaction (HOI) detection requires recognizing interaction phrases that may not appear as annotated categories during training. Recent vision-language HOI detectors improve semantic transfer by matching human-object features with text embeddings, but their predictions are often dominated by object affordance and phrase-level co-occurrence. As a result, a model may predict \\textit{cut cake} from the presence of a knife and a cake without verifying whether the hand, tool, target, contact pattern, and object state jointly support the action. We propose \\textbf{Scrip"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on HICO-DET, V-COCO, and open-vocabulary HOI splits show that ScriptHOI improves rare and unseen interaction recognition while substantially reducing affordance-conflict false positives.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the visual state tokenizer can reliably parse human-object pairs into accurate state tokens for the six slots and that script coverage and conflict estimates provide valid calibration without introducing new biases or missing critical visual cues.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ScriptHOI improves rare and unseen HOI recognition by decomposing phrases into state slots, using visual tokenization and slot-wise matching for script coverage and conflict to calibrate predictions and constrain training on incomplete labels.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Decomposing interaction phrases into state slots verifies multiple visual cues and improves rare and unseen human-object interaction detection.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6dcdb51ff20351e7ad5a0cfdc9f67c1dcdc67178829585d942dcadf506f08850"},"source":{"id":"2605.05057","kind":"arxiv","version":3},"verdict":{"id":"6f667bd3-8145-4ad6-bfe3-f36dba8bfad8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T01:40:01.161646Z","strongest_claim":"Experiments on HICO-DET, V-COCO, and open-vocabulary HOI splits show that ScriptHOI improves rare and unseen interaction recognition while substantially reducing affordance-conflict false positives.","one_line_summary":"ScriptHOI improves rare and unseen HOI recognition by decomposing phrases into state slots, using visual tokenization and slot-wise matching for script coverage and conflict to calibrate predictions and constrain training on incomplete labels.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the visual state tokenizer can reliably parse human-object pairs into accurate state tokens for the six slots and that script coverage and conflict estimates provide valid calibration without introducing new biases or missing critical visual cues.","pith_extraction_headline":"Decomposing interaction phrases into state slots verifies multiple visual cues and improves rare and unseen human-object interaction detection."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05057/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T10:38:08.925251Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.711658Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:52:20.973232Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2e9bee609381b8443b1946e3510c11be6ba4736b92645b2b2c03a9038f2a4e72"},"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":"6f667bd3-8145-4ad6-bfe3-f36dba8bfad8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sMTbcn7N5zRrsM5+fOJE6+c2vzg7TTwcfe31n6+q86OiKEwyX302ZWBdof+4+1MZUEEYNBQy0JUrWV3x8KAnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:32:04.276856Z"},"content_sha256":"d83d831ead0c274a939c577adc1f9ec0c1e89e4a135da8e773a6abc6c74e647c","schema_version":"1.0","event_id":"sha256:d83d831ead0c274a939c577adc1f9ec0c1e89e4a135da8e773a6abc6c74e647c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4PH2U7EJ5TS5WAGLAZ4SZDX4KG/bundle.json","state_url":"https://pith.science/pith/4PH2U7EJ5TS5WAGLAZ4SZDX4KG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4PH2U7EJ5TS5WAGLAZ4SZDX4KG/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":"2026-05-30T13:32:04Z","links":{"resolver":"https://pith.science/pith/4PH2U7EJ5TS5WAGLAZ4SZDX4KG","bundle":"https://pith.science/pith/4PH2U7EJ5TS5WAGLAZ4SZDX4KG/bundle.json","state":"https://pith.science/pith/4PH2U7EJ5TS5WAGLAZ4SZDX4KG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4PH2U7EJ5TS5WAGLAZ4SZDX4KG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4PH2U7EJ5TS5WAGLAZ4SZDX4KG","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":"ae304ecf7f00f4789847681c0eddaf2c8bfae8916d17565ba5f3950676dc8644","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T15:52:35Z","title_canon_sha256":"5ba83a70b6539342e3fa653a8d3464a206d40a03beaee8e71d5a75b31d7aef91"},"schema_version":"1.0","source":{"id":"2605.05057","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05057","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05057v3","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05057","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"4PH2U7EJ5TS5","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"4PH2U7EJ5TS5WAGL","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"4PH2U7EJ","created_at":"2026-05-27T01:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:d83d831ead0c274a939c577adc1f9ec0c1e89e4a135da8e773a6abc6c74e647c","target":"graph","created_at":"2026-05-27T01:04:58Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on HICO-DET, V-COCO, and open-vocabulary HOI splits show that ScriptHOI improves rare and unseen interaction recognition while substantially reducing affordance-conflict false positives."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the visual state tokenizer can reliably parse human-object pairs into accurate state tokens for the six slots and that script coverage and conflict estimates provide valid calibration without introducing new biases or missing critical visual cues."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ScriptHOI improves rare and unseen HOI recognition by decomposing phrases into state slots, using visual tokenization and slot-wise matching for script coverage and conflict to calibrate predictions and constrain training on incomplete labels."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Decomposing interaction phrases into state slots verifies multiple visual cues and improves rare and unseen human-object interaction detection."}],"snapshot_sha256":"6dcdb51ff20351e7ad5a0cfdc9f67c1dcdc67178829585d942dcadf506f08850"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T10:38:08.925251Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.711658Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T13:52:20.973232Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.05057/integrity.json","findings":[],"snapshot_sha256":"2e9bee609381b8443b1946e3510c11be6ba4736b92645b2b2c03a9038f2a4e72","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary human-object interaction (HOI) detection requires recognizing interaction phrases that may not appear as annotated categories during training. Recent vision-language HOI detectors improve semantic transfer by matching human-object features with text embeddings, but their predictions are often dominated by object affordance and phrase-level co-occurrence. As a result, a model may predict \\textit{cut cake} from the presence of a knife and a cake without verifying whether the hand, tool, target, contact pattern, and object state jointly support the action. We propose \\textbf{Scrip","authors_text":"Bao Ngoc Le, Linh Chi Vo, Minh Anh Nguyen, Quang Huy Tran, Suiyang Guang, Tuan Kiet Pham","cross_cats":[],"headline":"Decomposing interaction phrases into state slots verifies multiple visual cues and improves rare and unseen human-object interaction detection.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T15:52:35Z","title":"ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.05057","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-13T01:40:01.161646Z","id":"6f667bd3-8145-4ad6-bfe3-f36dba8bfad8","model_set":{"reader":"grok-4.3"},"one_line_summary":"ScriptHOI improves rare and unseen HOI recognition by decomposing phrases into state slots, using visual tokenization and slot-wise matching for script coverage and conflict to calibrate predictions and constrain training on incomplete labels.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Decomposing interaction phrases into state slots verifies multiple visual cues and improves rare and unseen human-object interaction detection.","strongest_claim":"Experiments on HICO-DET, V-COCO, and open-vocabulary HOI splits show that ScriptHOI improves rare and unseen interaction recognition while substantially reducing affordance-conflict false positives.","weakest_assumption":"That the visual state tokenizer can reliably parse human-object pairs into accurate state tokens for the six slots and that script coverage and conflict estimates provide valid calibration without introducing new biases or missing critical visual cues."}},"verdict_id":"6f667bd3-8145-4ad6-bfe3-f36dba8bfad8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7557803e97692d38d7d93d4a0996cc4c9629ae7d7c7648effc30fb45cc0a7ccc","target":"record","created_at":"2026-05-27T01:04:58Z","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":"ae304ecf7f00f4789847681c0eddaf2c8bfae8916d17565ba5f3950676dc8644","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T15:52:35Z","title_canon_sha256":"5ba83a70b6539342e3fa653a8d3464a206d40a03beaee8e71d5a75b31d7aef91"},"schema_version":"1.0","source":{"id":"2605.05057","kind":"arxiv","version":3}},"canonical_sha256":"e3cfaa7c89ece5db00cb06792c8efc5180aded54535774509e9f54a89bf8998a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3cfaa7c89ece5db00cb06792c8efc5180aded54535774509e9f54a89bf8998a","first_computed_at":"2026-05-27T01:04:58.799764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:58.799764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oK9z3rgM2+qImeefjnFRL6zmBFVuCbNrbU+OIxFnLvgb2+30cmjAZr4cjFQP58gi8mn05zePCobnxptqadGQAQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:58.800249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.05057","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7557803e97692d38d7d93d4a0996cc4c9629ae7d7c7648effc30fb45cc0a7ccc","sha256:d83d831ead0c274a939c577adc1f9ec0c1e89e4a135da8e773a6abc6c74e647c"],"state_sha256":"cb0b7a36c7d42fc95250660d1f54ca05cc989c34541e142197a9cdec05caeb49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"isKXfhQi1M3JS72aHGTcb8nhcEKCvarv5PEw2sBhAF70F0UczcWxTCbHh3dcFsrOLzMma/H+kk93I+LmLBWMCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:32:04.280968Z","bundle_sha256":"94440e5bdc686dadc5cafd84eb266a9dea5f4979452e15b6c612f89b4e9ecf45"}}