{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NZ5D42F6OIV7WJN6D6HTPHOVBS","short_pith_number":"pith:NZ5D42F6","canonical_record":{"source":{"id":"2306.13380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T09:02:25Z","cross_cats_sorted":[],"title_canon_sha256":"77245c165520179fd46626aef9fca3174d84ba6895caffba9983c2eca768a98f","abstract_canon_sha256":"ba837112ad793dac091d11b69f8ddc45d23a2c92c3562298269aa7eff3a99315"},"schema_version":"1.0"},"canonical_sha256":"6e7a3e68be722bfb25be1f8f379dd50c81c3119393636545a206585ef88b8c64","source":{"kind":"arxiv","id":"2306.13380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13380","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13380v1","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13380","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"pith_short_12","alias_value":"NZ5D42F6OIV7","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"pith_short_16","alias_value":"NZ5D42F6OIV7WJN6","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"pith_short_8","alias_value":"NZ5D42F6","created_at":"2026-07-05T06:24:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NZ5D42F6OIV7WJN6D6HTPHOVBS","target":"record","payload":{"canonical_record":{"source":{"id":"2306.13380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T09:02:25Z","cross_cats_sorted":[],"title_canon_sha256":"77245c165520179fd46626aef9fca3174d84ba6895caffba9983c2eca768a98f","abstract_canon_sha256":"ba837112ad793dac091d11b69f8ddc45d23a2c92c3562298269aa7eff3a99315"},"schema_version":"1.0"},"canonical_sha256":"6e7a3e68be722bfb25be1f8f379dd50c81c3119393636545a206585ef88b8c64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:04.853278Z","signature_b64":"GTSaRnOamtv77goWtcgZXR/iwDl4y1PuYIal6douhzdNoh4EyZgO/dRM0Qtd6TeewouiWmoFSQVPsXVjV0rRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e7a3e68be722bfb25be1f8f379dd50c81c3119393636545a206585ef88b8c64","last_reissued_at":"2026-07-05T06:24:04.852928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:04.852928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.13380","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":"2026-07-05T06:24:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVxMfjZ02ECpleb1NEydINpDvjGdyC8mVZ2lU/iUuE4cDHt7vfPmLOaRjwDn/7+mBybBmTwINEPwZsPun1iECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:46:13.741045Z"},"content_sha256":"759129c34a9f17c33bfffdc3f4c32bcfd8e6b6606be1606866e0f76504480f7c","schema_version":"1.0","event_id":"sha256:759129c34a9f17c33bfffdc3f4c32bcfd8e6b6606be1606866e0f76504480f7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NZ5D42F6OIV7WJN6D6HTPHOVBS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Hongshan Yu, Jingwen Wang, Ming Li, Tom Tongjia Chen, Wei Miao, Wei Sun, Zechuan Li, Zhengeng Yang","submitted_at":"2023-06-23T09:02:25Z","abstract_excerpt":"Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire knowledge from videos to furnish users with comprehensive and systematic instructions. However, existing methods have hitherto neglected the necessity of aligning spatiotemporal visual and linguistic signals, as well as the crucial interactional information between humans and objects. To tackle these limitations, we propose to combine large-scale pre-trained vision-language and video-language models, which serve to contribute stable and reliable multimodal data and facilitate effective spatiotemporal visual-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13380","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/2306.13380/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":"2026-07-05T06:24:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pori0bGyHG1AF+1/cq9cFVI69aKvK8NYMwHRudkB2ztSzvz8qpe4B4PL6RR6Sl9wfzxTsxA5JTP71N+8sD3GDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:46:13.741680Z"},"content_sha256":"63a4b55c23723786ff7605779f72f809a2591dd0a7266599d1fe72d3edc6709a","schema_version":"1.0","event_id":"sha256:63a4b55c23723786ff7605779f72f809a2591dd0a7266599d1fe72d3edc6709a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZ5D42F6OIV7WJN6D6HTPHOVBS/bundle.json","state_url":"https://pith.science/pith/NZ5D42F6OIV7WJN6D6HTPHOVBS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZ5D42F6OIV7WJN6D6HTPHOVBS/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":"2026-08-12T18:46:13Z","links":{"resolver":"https://pith.science/pith/NZ5D42F6OIV7WJN6D6HTPHOVBS","bundle":"https://pith.science/pith/NZ5D42F6OIV7WJN6D6HTPHOVBS/bundle.json","state":"https://pith.science/pith/NZ5D42F6OIV7WJN6D6HTPHOVBS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZ5D42F6OIV7WJN6D6HTPHOVBS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NZ5D42F6OIV7WJN6D6HTPHOVBS","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":"ba837112ad793dac091d11b69f8ddc45d23a2c92c3562298269aa7eff3a99315","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T09:02:25Z","title_canon_sha256":"77245c165520179fd46626aef9fca3174d84ba6895caffba9983c2eca768a98f"},"schema_version":"1.0","source":{"id":"2306.13380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13380","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13380v1","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13380","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"pith_short_12","alias_value":"NZ5D42F6OIV7","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"pith_short_16","alias_value":"NZ5D42F6OIV7WJN6","created_at":"2026-07-05T06:24:04Z"},{"alias_kind":"pith_short_8","alias_value":"NZ5D42F6","created_at":"2026-07-05T06:24:04Z"}],"graph_snapshots":[{"event_id":"sha256:63a4b55c23723786ff7605779f72f809a2591dd0a7266599d1fe72d3edc6709a","target":"graph","created_at":"2026-07-05T06:24:04Z","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/2306.13380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire knowledge from videos to furnish users with comprehensive and systematic instructions. However, existing methods have hitherto neglected the necessity of aligning spatiotemporal visual and linguistic signals, as well as the crucial interactional information between humans and objects. To tackle these limitations, we propose to combine large-scale pre-trained vision-language and video-language models, which serve to contribute stable and reliable multimodal data and facilitate effective spatiotemporal visual-","authors_text":"Chen Chen, Hongshan Yu, Jingwen Wang, Ming Li, Tom Tongjia Chen, Wei Miao, Wei Sun, Zechuan Li, Zhengeng Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T09:02:25Z","title":"First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13380","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":"sha256:759129c34a9f17c33bfffdc3f4c32bcfd8e6b6606be1606866e0f76504480f7c","target":"record","created_at":"2026-07-05T06:24:04Z","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":"ba837112ad793dac091d11b69f8ddc45d23a2c92c3562298269aa7eff3a99315","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T09:02:25Z","title_canon_sha256":"77245c165520179fd46626aef9fca3174d84ba6895caffba9983c2eca768a98f"},"schema_version":"1.0","source":{"id":"2306.13380","kind":"arxiv","version":1}},"canonical_sha256":"6e7a3e68be722bfb25be1f8f379dd50c81c3119393636545a206585ef88b8c64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e7a3e68be722bfb25be1f8f379dd50c81c3119393636545a206585ef88b8c64","first_computed_at":"2026-07-05T06:24:04.852928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:04.852928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GTSaRnOamtv77goWtcgZXR/iwDl4y1PuYIal6douhzdNoh4EyZgO/dRM0Qtd6TeewouiWmoFSQVPsXVjV0rRDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:04.853278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.13380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:759129c34a9f17c33bfffdc3f4c32bcfd8e6b6606be1606866e0f76504480f7c","sha256:63a4b55c23723786ff7605779f72f809a2591dd0a7266599d1fe72d3edc6709a"],"state_sha256":"416893ee21a399fd32cc7dd135cfa0e1de85a7d0ce2fbbd7d4db1c8f5b723f0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p04qTITnjedVNU6MK0DRBO8Bj3Z4Pva2iF1q57thYiZaBTATvs3XspKnqGfMzNudCiiNzmlEpeo3snsLIWfODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:46:13.747531Z","bundle_sha256":"fa4bbbd1ec97579c901a308ee1e7a8c428b3ca39609510e42bf07bb6d12813db"}}