{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YGG3NHMDTZ2EGPALZXSFFPZH4Y","short_pith_number":"pith:YGG3NHMD","canonical_record":{"source":{"id":"2310.10125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T07:08:39Z","cross_cats_sorted":[],"title_canon_sha256":"0888f55f5a5bee897fbd7f901b9b5b8709876be838c3f8a2c34c26b8fede9cf6","abstract_canon_sha256":"7a4816e28b14c6075fbd0ac5af74d9e96f3da19fa414e9522320b27452e6f9e9"},"schema_version":"1.0"},"canonical_sha256":"c18db69d839e74433c0bcde452bf27e61572821a34b127b26c59e1cea5684ecb","source":{"kind":"arxiv","id":"2310.10125","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10125","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10125v1","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10125","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"YGG3NHMDTZ2E","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"YGG3NHMDTZ2EGPAL","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"YGG3NHMD","created_at":"2026-07-05T07:01:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YGG3NHMDTZ2EGPALZXSFFPZH4Y","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T07:08:39Z","cross_cats_sorted":[],"title_canon_sha256":"0888f55f5a5bee897fbd7f901b9b5b8709876be838c3f8a2c34c26b8fede9cf6","abstract_canon_sha256":"7a4816e28b14c6075fbd0ac5af74d9e96f3da19fa414e9522320b27452e6f9e9"},"schema_version":"1.0"},"canonical_sha256":"c18db69d839e74433c0bcde452bf27e61572821a34b127b26c59e1cea5684ecb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:15.591804Z","signature_b64":"p5DDtpuhnpXryrD0Hn6XC3quNYU6YTKme+RI8MS1eYUPP/OH/wimY8U2BSGnOeoe0CYO8UeOfXIkWJ0t270VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c18db69d839e74433c0bcde452bf27e61572821a34b127b26c59e1cea5684ecb","last_reissued_at":"2026-07-05T07:01:15.591253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:15.591253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10125","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":"2026-07-05T07:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2TF4xfcpWZIQGqdNRA7cUpuhRlKBXLYTIkoj1OnYooyn9CW17jOSTWRng4CtISj0z3ZRFQSsKpc5SRvyPvk4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:15:00.568522Z"},"content_sha256":"ee5760605ac878e12884422a0d2fb04ff9309b00cff8229c347bc40c0443fbd1","schema_version":"1.0","event_id":"sha256:ee5760605ac878e12884422a0d2fb04ff9309b00cff8229c347bc40c0443fbd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YGG3NHMDTZ2EGPALZXSFFPZH4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-shot Action Recognition with Captioning Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Deli Zhao, Hangjie Yuan, Nong Sang, Shiwei Zhang, Xiang Wang, Yingya Zhang","submitted_at":"2023-10-16T07:08:39Z","abstract_excerpt":"Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual modality input due to the high cost of annotating additional textual descriptions. In this paper, we develop an effective plug-and-play framework called CapFSAR to exploit the knowledge of multimodal models without manually annotating text. To be specific, we first utilize a captioning foundation model (i.e., BLIP) to extract visual features and automatically gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10125","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/2310.10125/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":"2026-07-05T07:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xso5u9l5NHqBHZMvT1srXTfW3CB4hZTuAA6Xn5Kx5wB5DE/gZ9ciCzr8E64aKCACnSdKwjNpjmzZ11G1zZPPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:15:00.568923Z"},"content_sha256":"4227f5661f59da1f724cea57af00dfd74a91cc0064573305b452ccab59a487f8","schema_version":"1.0","event_id":"sha256:4227f5661f59da1f724cea57af00dfd74a91cc0064573305b452ccab59a487f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/bundle.json","state_url":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/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":"2026-08-07T22:15:00Z","links":{"resolver":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y","bundle":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/bundle.json","state":"https://pith.science/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGG3NHMDTZ2EGPALZXSFFPZH4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YGG3NHMDTZ2EGPALZXSFFPZH4Y","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":"7a4816e28b14c6075fbd0ac5af74d9e96f3da19fa414e9522320b27452e6f9e9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T07:08:39Z","title_canon_sha256":"0888f55f5a5bee897fbd7f901b9b5b8709876be838c3f8a2c34c26b8fede9cf6"},"schema_version":"1.0","source":{"id":"2310.10125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10125","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10125v1","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10125","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"YGG3NHMDTZ2E","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"YGG3NHMDTZ2EGPAL","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"YGG3NHMD","created_at":"2026-07-05T07:01:15Z"}],"graph_snapshots":[{"event_id":"sha256:4227f5661f59da1f724cea57af00dfd74a91cc0064573305b452ccab59a487f8","target":"graph","created_at":"2026-07-05T07:01:15Z","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/2310.10125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual modality input due to the high cost of annotating additional textual descriptions. In this paper, we develop an effective plug-and-play framework called CapFSAR to exploit the knowledge of multimodal models without manually annotating text. To be specific, we first utilize a captioning foundation model (i.e., BLIP) to extract visual features and automatically gener","authors_text":"Changxin Gao, Deli Zhao, Hangjie Yuan, Nong Sang, Shiwei Zhang, Xiang Wang, Yingya Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T07:08:39Z","title":"Few-shot Action Recognition with Captioning Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10125","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:ee5760605ac878e12884422a0d2fb04ff9309b00cff8229c347bc40c0443fbd1","target":"record","created_at":"2026-07-05T07:01:15Z","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":"7a4816e28b14c6075fbd0ac5af74d9e96f3da19fa414e9522320b27452e6f9e9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T07:08:39Z","title_canon_sha256":"0888f55f5a5bee897fbd7f901b9b5b8709876be838c3f8a2c34c26b8fede9cf6"},"schema_version":"1.0","source":{"id":"2310.10125","kind":"arxiv","version":1}},"canonical_sha256":"c18db69d839e74433c0bcde452bf27e61572821a34b127b26c59e1cea5684ecb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c18db69d839e74433c0bcde452bf27e61572821a34b127b26c59e1cea5684ecb","first_computed_at":"2026-07-05T07:01:15.591253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:15.591253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p5DDtpuhnpXryrD0Hn6XC3quNYU6YTKme+RI8MS1eYUPP/OH/wimY8U2BSGnOeoe0CYO8UeOfXIkWJ0t270VBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:15.591804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee5760605ac878e12884422a0d2fb04ff9309b00cff8229c347bc40c0443fbd1","sha256:4227f5661f59da1f724cea57af00dfd74a91cc0064573305b452ccab59a487f8"],"state_sha256":"5175a4e536111961f3049fa0e9d28ad181bc0fcd27544607c4fd468dc4814331"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"36XW/Iz1FdxsWHJpzQjt7RXHgKs/aQ1VeG3VurDwsKQVO5LPDzFejPJogWvvYbIQUeZQm4DldbQDwdEaAS/GDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:15:00.571685Z","bundle_sha256":"2aab432ec77d4a650d2bcfbd7f36db35d73ac0bd48f04684ece0cf0941af6711"}}