{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6AOIKNYEYAIA5IWD46KOQWUGW4","short_pith_number":"pith:6AOIKNYE","canonical_record":{"source":{"id":"2104.05845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T22:20:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"242f92080a28a9e78c4d043fc7a1199f9c300843887e9c962ae09d7e7c30f7ef","abstract_canon_sha256":"33adfbb970ec1cdd6392e84d013d9661315758ab57d5d23cb417b3f2d2d1c5f5"},"schema_version":"1.0"},"canonical_sha256":"f01c853704c0100ea2c3e794e85a86b7066c8614e22cac10d9146945a3f4a95c","source":{"kind":"arxiv","id":"2104.05845","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05845","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05845v2","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05845","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"6AOIKNYEYAIA","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"6AOIKNYEYAIA5IWD","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"6AOIKNYE","created_at":"2026-07-05T03:13:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6AOIKNYEYAIA5IWD46KOQWUGW4","target":"record","payload":{"canonical_record":{"source":{"id":"2104.05845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T22:20:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"242f92080a28a9e78c4d043fc7a1199f9c300843887e9c962ae09d7e7c30f7ef","abstract_canon_sha256":"33adfbb970ec1cdd6392e84d013d9661315758ab57d5d23cb417b3f2d2d1c5f5"},"schema_version":"1.0"},"canonical_sha256":"f01c853704c0100ea2c3e794e85a86b7066c8614e22cac10d9146945a3f4a95c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:02.841860Z","signature_b64":"mUQIFAoPeuyNey5YSkp4sB6oLSzhUB37+s1VkCPeIoQG+lr0h1PxOy6dc2F3UvI0xwE9EYGIUGt4eySpVIZkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f01c853704c0100ea2c3e794e85a86b7066c8614e22cac10d9146945a3f4a95c","last_reissued_at":"2026-07-05T03:13:02.841432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:02.841432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.05845","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aXE46y81bwx6su8HaZm1ujr/LgQ0ufIO5VIwv1FBJ+fpTVu/sHxM5BmdzG6HAWeAnTPMhXPkFIC1I/DSCO67Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:12:59.420188Z"},"content_sha256":"4f7e9f543abe70164ee470ceee4f0fe3015ab9148dedab7cff81a80566c0574f","schema_version":"1.0","event_id":"sha256:4f7e9f543abe70164ee470ceee4f0fe3015ab9148dedab7cff81a80566c0574f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6AOIKNYEYAIA5IWD46KOQWUGW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Goal-Step Inference using wikiHow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Artemis Panagopoulou, Chris Callison-Burch, Li Zhang, Mark Yatskar, Qing Lyu, Yue Yang","submitted_at":"2021-04-12T22:20:09Z","abstract_excerpt":"Understanding what sequence of steps are needed to complete a goal can help artificial intelligence systems reason about human activities. Past work in NLP has examined the task of goal-step inference for text. We introduce the visual analogue. We propose the Visual Goal-Step Inference (VGSI) task, where a model is given a textual goal and must choose which of four images represents a plausible step towards that goal. With a new dataset harvested from wikiHow consisting of 772,277 images representing human actions, we show that our task is challenging for state-of-the-art multimodal models. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05845","kind":"arxiv","version":2},"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/2104.05845/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":"2026-07-05T03:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2eR3qq70+ATCRaOWRJbRdMuqPrBzl8swShoJ+YMt5naQAadrJw+uqM5NO60jijD98HNwhdG3OALT4rh7MK5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:12:59.420716Z"},"content_sha256":"4027920371fe80b3d8ac94a09f5304d74ea3e4dd473fe3dd3a96913292f44c5d","schema_version":"1.0","event_id":"sha256:4027920371fe80b3d8ac94a09f5304d74ea3e4dd473fe3dd3a96913292f44c5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6AOIKNYEYAIA5IWD46KOQWUGW4/bundle.json","state_url":"https://pith.science/pith/6AOIKNYEYAIA5IWD46KOQWUGW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6AOIKNYEYAIA5IWD46KOQWUGW4/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":"2026-08-18T06:12:59Z","links":{"resolver":"https://pith.science/pith/6AOIKNYEYAIA5IWD46KOQWUGW4","bundle":"https://pith.science/pith/6AOIKNYEYAIA5IWD46KOQWUGW4/bundle.json","state":"https://pith.science/pith/6AOIKNYEYAIA5IWD46KOQWUGW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6AOIKNYEYAIA5IWD46KOQWUGW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6AOIKNYEYAIA5IWD46KOQWUGW4","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":"33adfbb970ec1cdd6392e84d013d9661315758ab57d5d23cb417b3f2d2d1c5f5","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T22:20:09Z","title_canon_sha256":"242f92080a28a9e78c4d043fc7a1199f9c300843887e9c962ae09d7e7c30f7ef"},"schema_version":"1.0","source":{"id":"2104.05845","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05845","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05845v2","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05845","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"6AOIKNYEYAIA","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"6AOIKNYEYAIA5IWD","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"6AOIKNYE","created_at":"2026-07-05T03:13:02Z"}],"graph_snapshots":[{"event_id":"sha256:4027920371fe80b3d8ac94a09f5304d74ea3e4dd473fe3dd3a96913292f44c5d","target":"graph","created_at":"2026-07-05T03:13:02Z","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/2104.05845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding what sequence of steps are needed to complete a goal can help artificial intelligence systems reason about human activities. Past work in NLP has examined the task of goal-step inference for text. We introduce the visual analogue. We propose the Visual Goal-Step Inference (VGSI) task, where a model is given a textual goal and must choose which of four images represents a plausible step towards that goal. With a new dataset harvested from wikiHow consisting of 772,277 images representing human actions, we show that our task is challenging for state-of-the-art multimodal models. Mo","authors_text":"Artemis Panagopoulou, Chris Callison-Burch, Li Zhang, Mark Yatskar, Qing Lyu, Yue Yang","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T22:20:09Z","title":"Visual Goal-Step Inference using wikiHow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05845","kind":"arxiv","version":2},"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":"sha256:4f7e9f543abe70164ee470ceee4f0fe3015ab9148dedab7cff81a80566c0574f","target":"record","created_at":"2026-07-05T03:13:02Z","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":"33adfbb970ec1cdd6392e84d013d9661315758ab57d5d23cb417b3f2d2d1c5f5","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T22:20:09Z","title_canon_sha256":"242f92080a28a9e78c4d043fc7a1199f9c300843887e9c962ae09d7e7c30f7ef"},"schema_version":"1.0","source":{"id":"2104.05845","kind":"arxiv","version":2}},"canonical_sha256":"f01c853704c0100ea2c3e794e85a86b7066c8614e22cac10d9146945a3f4a95c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f01c853704c0100ea2c3e794e85a86b7066c8614e22cac10d9146945a3f4a95c","first_computed_at":"2026-07-05T03:13:02.841432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:02.841432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mUQIFAoPeuyNey5YSkp4sB6oLSzhUB37+s1VkCPeIoQG+lr0h1PxOy6dc2F3UvI0xwE9EYGIUGt4eySpVIZkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:02.841860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.05845","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f7e9f543abe70164ee470ceee4f0fe3015ab9148dedab7cff81a80566c0574f","sha256:4027920371fe80b3d8ac94a09f5304d74ea3e4dd473fe3dd3a96913292f44c5d"],"state_sha256":"5d7777e9db15742f2a0692da12e3ad2a1c8b10bc6c3aa2c02c9ab227bf3540f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aFNxRpvkZITPs3l3UOK2ZDqr0TVnMR/43n0qeBEIQSs2YpESWl7L+hLE8Bcz+dQnDxOnfxd1CdOBGjvo1WpNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:12:59.425955Z","bundle_sha256":"37b1dff0775e5bb9e51c73c8569e3fe392af684fd7ae192d693d2af91206ae1a"}}