{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CXOBJE362M2EBMMWDYUBPR6VBB","short_pith_number":"pith:CXOBJE36","canonical_record":{"source":{"id":"2304.04688","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T16:08:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"395ed7091d71b0f2e8bf736940ab285c9bf732b305ea30a72531cd45677b7b58","abstract_canon_sha256":"e3125b0b05a6cbcf703ac01348c489d56a7be3a45297267741e7a2d592ac2d44"},"schema_version":"1.0"},"canonical_sha256":"15dc14937ed33440b1961e2817c7d50870f9c8d7bf6c315cc2149bef4cb5fc9f","source":{"kind":"arxiv","id":"2304.04688","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04688","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04688v4","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04688","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"CXOBJE362M2E","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"pith_short_16","alias_value":"CXOBJE362M2EBMMW","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"pith_short_8","alias_value":"CXOBJE36","created_at":"2026-07-05T06:52:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CXOBJE362M2EBMMWDYUBPR6VBB","target":"record","payload":{"canonical_record":{"source":{"id":"2304.04688","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T16:08:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"395ed7091d71b0f2e8bf736940ab285c9bf732b305ea30a72531cd45677b7b58","abstract_canon_sha256":"e3125b0b05a6cbcf703ac01348c489d56a7be3a45297267741e7a2d592ac2d44"},"schema_version":"1.0"},"canonical_sha256":"15dc14937ed33440b1961e2817c7d50870f9c8d7bf6c315cc2149bef4cb5fc9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:22.178440Z","signature_b64":"RoVhvoR0okQAycYKUErThywglJqQMk7I1Yc9Kqrge03De+qM3gVk6KDr4gJwQDJxK7tyqq3XV402QrQlCaNRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15dc14937ed33440b1961e2817c7d50870f9c8d7bf6c315cc2149bef4cb5fc9f","last_reissued_at":"2026-07-05T06:52:22.178027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:22.178027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.04688","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jBYAVk/KEz/mxjzN3uU8aK9YhEqHIYNqY7JaK49/dhSK/17v7J9ub2tFYk/RbtAw6kN2LP3OVi3cHGL7XvZhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:45:24.520640Z"},"content_sha256":"b39f2232ecaa7b4bd029e3925cd6a10755b94382bfd0fc56a1481a99bf44b03d","schema_version":"1.0","event_id":"sha256:b39f2232ecaa7b4bd029e3925cd6a10755b94382bfd0fc56a1481a99bf44b03d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CXOBJE362M2EBMMWDYUBPR6VBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gueter Josmy Faure, Jheng-Hsien Yeh, Min-Hung Chen, Shang-Hong Lai, Wei-Jhe Huang","submitted_at":"2023-04-10T16:08:59Z","abstract_excerpt":"The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most of the existing methods adopt fully-supervised learning, which requires a large amount of training data, making it very difficult to achieve zero-shot learning. In this paper, we propose to utilize a pre-trained visual-language model to extract the representative image and text features, and model the relationship between these features through different interaction modules to obtain the interaction feature. In additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04688","kind":"arxiv","version":4},"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/2304.04688/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":"2026-07-05T06:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8UlzEOvzSv8eCu4SiiPmmEwJVyCT1mLbW7mZfykWcBeP6ATVYjWxtpE3x+q4fqZ+q43n6ytK66NTf5PkZHlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:45:24.521030Z"},"content_sha256":"0a5c50ea6a35e6476c6e0ac9ddae180f3bdfc5b83cb1ce190e4f27104e3dcc1e","schema_version":"1.0","event_id":"sha256:0a5c50ea6a35e6476c6e0ac9ddae180f3bdfc5b83cb1ce190e4f27104e3dcc1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/bundle.json","state_url":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXOBJE362M2EBMMWDYUBPR6VBB/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":"2026-07-07T05:45:24Z","links":{"resolver":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB","bundle":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/bundle.json","state":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXOBJE362M2EBMMWDYUBPR6VBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CXOBJE362M2EBMMWDYUBPR6VBB","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":"e3125b0b05a6cbcf703ac01348c489d56a7be3a45297267741e7a2d592ac2d44","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T16:08:59Z","title_canon_sha256":"395ed7091d71b0f2e8bf736940ab285c9bf732b305ea30a72531cd45677b7b58"},"schema_version":"1.0","source":{"id":"2304.04688","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04688","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04688v4","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04688","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"CXOBJE362M2E","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"pith_short_16","alias_value":"CXOBJE362M2EBMMW","created_at":"2026-07-05T06:52:22Z"},{"alias_kind":"pith_short_8","alias_value":"CXOBJE36","created_at":"2026-07-05T06:52:22Z"}],"graph_snapshots":[{"event_id":"sha256:0a5c50ea6a35e6476c6e0ac9ddae180f3bdfc5b83cb1ce190e4f27104e3dcc1e","target":"graph","created_at":"2026-07-05T06:52:22Z","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/2304.04688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most of the existing methods adopt fully-supervised learning, which requires a large amount of training data, making it very difficult to achieve zero-shot learning. In this paper, we propose to utilize a pre-trained visual-language model to extract the representative image and text features, and model the relationship between these features through different interaction modules to obtain the interaction feature. In additi","authors_text":"Gueter Josmy Faure, Jheng-Hsien Yeh, Min-Hung Chen, Shang-Hong Lai, Wei-Jhe Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T16:08:59Z","title":"Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04688","kind":"arxiv","version":4},"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:b39f2232ecaa7b4bd029e3925cd6a10755b94382bfd0fc56a1481a99bf44b03d","target":"record","created_at":"2026-07-05T06:52:22Z","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":"e3125b0b05a6cbcf703ac01348c489d56a7be3a45297267741e7a2d592ac2d44","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T16:08:59Z","title_canon_sha256":"395ed7091d71b0f2e8bf736940ab285c9bf732b305ea30a72531cd45677b7b58"},"schema_version":"1.0","source":{"id":"2304.04688","kind":"arxiv","version":4}},"canonical_sha256":"15dc14937ed33440b1961e2817c7d50870f9c8d7bf6c315cc2149bef4cb5fc9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15dc14937ed33440b1961e2817c7d50870f9c8d7bf6c315cc2149bef4cb5fc9f","first_computed_at":"2026-07-05T06:52:22.178027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:22.178027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RoVhvoR0okQAycYKUErThywglJqQMk7I1Yc9Kqrge03De+qM3gVk6KDr4gJwQDJxK7tyqq3XV402QrQlCaNRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:22.178440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.04688","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b39f2232ecaa7b4bd029e3925cd6a10755b94382bfd0fc56a1481a99bf44b03d","sha256:0a5c50ea6a35e6476c6e0ac9ddae180f3bdfc5b83cb1ce190e4f27104e3dcc1e"],"state_sha256":"3c0dd10b74587d1f6aacd4b81a09932e8945e940846aa9eb0b8be97b247a160e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hroPyXojlI90usQCRnRyHDmycLBriqCXWOU3suaKpJUetmldo2pU0cT04AR8KRD/VjehzRMS0J8ACtVfgOumCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:45:24.523190Z","bundle_sha256":"9a1c596bb9ab80c12d7d8af3c162a04c508c63e0b41d9f5bf30d75d2bd115329"}}