{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KB44M4Z533YQLWBRJASNOCPA2N","short_pith_number":"pith:KB44M4Z5","canonical_record":{"source":{"id":"2404.15785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T10:17:13Z","cross_cats_sorted":[],"title_canon_sha256":"57ae605af1ff74a5af13d9806e66529cb6ab1303e7a691f01b24316654d67ec6","abstract_canon_sha256":"fdf2b232eb32df3de328895ad74e73f9c908fc97a9a53187607856e843c44c3a"},"schema_version":"1.0"},"canonical_sha256":"5079c6733ddef105d8314824d709e0d3643a24a99f48d60a6baaa584c11e2842","source":{"kind":"arxiv","id":"2404.15785","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15785","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15785v1","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15785","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_12","alias_value":"KB44M4Z533YQ","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_16","alias_value":"KB44M4Z533YQLWBR","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_8","alias_value":"KB44M4Z5","created_at":"2026-07-05T08:11:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KB44M4Z533YQLWBRJASNOCPA2N","target":"record","payload":{"canonical_record":{"source":{"id":"2404.15785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T10:17:13Z","cross_cats_sorted":[],"title_canon_sha256":"57ae605af1ff74a5af13d9806e66529cb6ab1303e7a691f01b24316654d67ec6","abstract_canon_sha256":"fdf2b232eb32df3de328895ad74e73f9c908fc97a9a53187607856e843c44c3a"},"schema_version":"1.0"},"canonical_sha256":"5079c6733ddef105d8314824d709e0d3643a24a99f48d60a6baaa584c11e2842","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:45.194158Z","signature_b64":"/F4z1spSL6eTCffiW+3SMtIRwb4VuwoKsbudjhaRE7JaO9oUNa5KthiY1UG1n1oYK/deZqVc53gwZoIh1m65Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5079c6733ddef105d8314824d709e0d3643a24a99f48d60a6baaa584c11e2842","last_reissued_at":"2026-07-05T08:11:45.193681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:45.193681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.15785","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":"2026-07-05T08:11:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jOYQ7Cb4xeF9N0rvyK3zoAt4VFaUfuFHVsCVbTnk3FiXXhtsT2ljCsTtCIcIqZ54SSupXYjN6ZR6DCLPwowdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T13:06:55.661753Z"},"content_sha256":"0a8431a9c900494d0ac5a547ce86e5db267177dc767a9be0b781445607773b9f","schema_version":"1.0","event_id":"sha256:0a8431a9c900494d0ac5a547ce86e5db267177dc767a9be0b781445607773b9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KB44M4Z533YQLWBRJASNOCPA2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunping Wang, Jiaming Lei, Jun Xiao, Lin Li, Long Chen","submitted_at":"2024-04-24T10:17:13Z","abstract_excerpt":"Benefiting from strong generalization ability, pre-trained vision language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple recognition tasks, grounded situation recognition (GSR) requires the model not only to classify salient activity (verb) in the image, but also to detect all semantic roles that participate in the action. This complex task usually involves three steps: verb recognition, semantic role grounding, and noun recognition. Directly employing class-based prompts with VLMs and grounding models for this task suffers from several li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15785","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/2404.15785/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":"2026-07-05T08:11:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9od3PzS+FLLPCGhMDFjgc3QRm5AAnIgVBBus/iOidITWcNPFvi/wk8gwz3/XAjKgWsy7zYa3f4/5VU+PYz40Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T13:06:55.662143Z"},"content_sha256":"e0d6e9b341d89c70f7adc5001139215c0f99b4e631eeed6b74343073f00f8ef8","schema_version":"1.0","event_id":"sha256:e0d6e9b341d89c70f7adc5001139215c0f99b4e631eeed6b74343073f00f8ef8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KB44M4Z533YQLWBRJASNOCPA2N/bundle.json","state_url":"https://pith.science/pith/KB44M4Z533YQLWBRJASNOCPA2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KB44M4Z533YQLWBRJASNOCPA2N/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":"2026-07-10T13:06:55Z","links":{"resolver":"https://pith.science/pith/KB44M4Z533YQLWBRJASNOCPA2N","bundle":"https://pith.science/pith/KB44M4Z533YQLWBRJASNOCPA2N/bundle.json","state":"https://pith.science/pith/KB44M4Z533YQLWBRJASNOCPA2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KB44M4Z533YQLWBRJASNOCPA2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KB44M4Z533YQLWBRJASNOCPA2N","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":"fdf2b232eb32df3de328895ad74e73f9c908fc97a9a53187607856e843c44c3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T10:17:13Z","title_canon_sha256":"57ae605af1ff74a5af13d9806e66529cb6ab1303e7a691f01b24316654d67ec6"},"schema_version":"1.0","source":{"id":"2404.15785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15785","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15785v1","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15785","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_12","alias_value":"KB44M4Z533YQ","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_16","alias_value":"KB44M4Z533YQLWBR","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_8","alias_value":"KB44M4Z5","created_at":"2026-07-05T08:11:45Z"}],"graph_snapshots":[{"event_id":"sha256:e0d6e9b341d89c70f7adc5001139215c0f99b4e631eeed6b74343073f00f8ef8","target":"graph","created_at":"2026-07-05T08:11:45Z","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/2404.15785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benefiting from strong generalization ability, pre-trained vision language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple recognition tasks, grounded situation recognition (GSR) requires the model not only to classify salient activity (verb) in the image, but also to detect all semantic roles that participate in the action. This complex task usually involves three steps: verb recognition, semantic role grounding, and noun recognition. Directly employing class-based prompts with VLMs and grounding models for this task suffers from several li","authors_text":"Chunping Wang, Jiaming Lei, Jun Xiao, Lin Li, Long Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T10:17:13Z","title":"Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15785","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":"sha256:0a8431a9c900494d0ac5a547ce86e5db267177dc767a9be0b781445607773b9f","target":"record","created_at":"2026-07-05T08:11:45Z","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":"fdf2b232eb32df3de328895ad74e73f9c908fc97a9a53187607856e843c44c3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T10:17:13Z","title_canon_sha256":"57ae605af1ff74a5af13d9806e66529cb6ab1303e7a691f01b24316654d67ec6"},"schema_version":"1.0","source":{"id":"2404.15785","kind":"arxiv","version":1}},"canonical_sha256":"5079c6733ddef105d8314824d709e0d3643a24a99f48d60a6baaa584c11e2842","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5079c6733ddef105d8314824d709e0d3643a24a99f48d60a6baaa584c11e2842","first_computed_at":"2026-07-05T08:11:45.193681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:45.193681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/F4z1spSL6eTCffiW+3SMtIRwb4VuwoKsbudjhaRE7JaO9oUNa5KthiY1UG1n1oYK/deZqVc53gwZoIh1m65Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:45.194158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a8431a9c900494d0ac5a547ce86e5db267177dc767a9be0b781445607773b9f","sha256:e0d6e9b341d89c70f7adc5001139215c0f99b4e631eeed6b74343073f00f8ef8"],"state_sha256":"97e9c6cad7d835fe42425f69049093402d5dba8208e2c0dfcbbb12df96d8da3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HHUxuQP8ih0VacMMyi2KBnR26/gTtBQGkUJAsLUpwo6orbeeDBGAWFnjhe4cfd8SI7GO54PI73h+hq89JB/TAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T13:06:55.664280Z","bundle_sha256":"1c3c50d0e4518919f490369794513800cade40a1d5baab18761d783ddff57081"}}