{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:4PHHS26EVX3TT4SS3MJZIE2JLP","short_pith_number":"pith:4PHHS26E","canonical_record":{"source":{"id":"1605.03324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-11T08:22:06Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"2806b7dd355529767a3fcefb5ce182cf833e849164ca7439d5c5dcafe03d8fba","abstract_canon_sha256":"578c23b88bba3ae90cae857cbf498137c5670c6201781308be8df005af171184"},"schema_version":"1.0"},"canonical_sha256":"e3ce796bc4adf739f252db139413495bf7f7e1b96ab94b0c145ae83b35598b97","source":{"kind":"arxiv","id":"1605.03324","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.03324","created_at":"2026-05-18T01:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"1605.03324v1","created_at":"2026-05-18T01:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.03324","created_at":"2026-05-18T01:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"4PHHS26EVX3T","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"4PHHS26EVX3TT4SS","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"4PHHS26E","created_at":"2026-05-18T12:29:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:4PHHS26EVX3TT4SS3MJZIE2JLP","target":"record","payload":{"canonical_record":{"source":{"id":"1605.03324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-11T08:22:06Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"2806b7dd355529767a3fcefb5ce182cf833e849164ca7439d5c5dcafe03d8fba","abstract_canon_sha256":"578c23b88bba3ae90cae857cbf498137c5670c6201781308be8df005af171184"},"schema_version":"1.0"},"canonical_sha256":"e3ce796bc4adf739f252db139413495bf7f7e1b96ab94b0c145ae83b35598b97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:05.653065Z","signature_b64":"ZEyPY7PA82iXIt4jdSaMggzPN3lEQF7G1/OF3sMa9uToHd3B8RqpeiL/bg4pUA24vdYy1d7tnW50N1JEB4M6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ce796bc4adf739f252db139413495bf7f7e1b96ab94b0c145ae83b35598b97","last_reissued_at":"2026-05-18T01:15:05.652466Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:05.652466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.03324","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":"2026-05-18T01:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RwnIohWmIsNY6nG60rZaIsvi/eAdnQNTfS4vRcIT1SJnvqw8TISL1K90MYF6kN9xoFO9qNtmeUamhNtLdcA/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:20:31.058817Z"},"content_sha256":"86f09b010ba2172ff61a9b1056a4b3c83b3ad7b6444c1d6d4803ed1d86755486","schema_version":"1.0","event_id":"sha256:86f09b010ba2172ff61a9b1056a4b3c83b3ad7b6444c1d6d4803ed1d86755486"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:4PHHS26EVX3TT4SS3MJZIE2JLP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Semantic Action Discovery from Video Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.CV","authors_text":"Amir Roshan Zamir, Ashutosh Saxena, Chenxia Wu, Ozan Sener, Silvio Savarese","submitted_at":"2016-05-11T08:22:06Z","abstract_excerpt":"Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet.\n  We propose a method for parsing a video into such semantic steps in an unsupervised way. Our method is capable of providing a semantic \"storyline\" of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. Our method ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.03324","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":""},"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":"2026-05-18T01:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BnLJ9oJQBpNx9ggMG9WBxOF2kRI/e37v0Gy4+F33b1ItVvLO5kkCKGlGCG9OO58uaBMF9a8wWBkbLNWGcvEdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:20:31.059209Z"},"content_sha256":"884ec37fb4f7470f7ae4fc61c2ce7d2761d3e6537f03951dd338ee14d139617f","schema_version":"1.0","event_id":"sha256:884ec37fb4f7470f7ae4fc61c2ce7d2761d3e6537f03951dd338ee14d139617f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4PHHS26EVX3TT4SS3MJZIE2JLP/bundle.json","state_url":"https://pith.science/pith/4PHHS26EVX3TT4SS3MJZIE2JLP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4PHHS26EVX3TT4SS3MJZIE2JLP/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":"2026-05-27T19:20:31Z","links":{"resolver":"https://pith.science/pith/4PHHS26EVX3TT4SS3MJZIE2JLP","bundle":"https://pith.science/pith/4PHHS26EVX3TT4SS3MJZIE2JLP/bundle.json","state":"https://pith.science/pith/4PHHS26EVX3TT4SS3MJZIE2JLP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4PHHS26EVX3TT4SS3MJZIE2JLP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:4PHHS26EVX3TT4SS3MJZIE2JLP","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":"578c23b88bba3ae90cae857cbf498137c5670c6201781308be8df005af171184","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-11T08:22:06Z","title_canon_sha256":"2806b7dd355529767a3fcefb5ce182cf833e849164ca7439d5c5dcafe03d8fba"},"schema_version":"1.0","source":{"id":"1605.03324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.03324","created_at":"2026-05-18T01:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"1605.03324v1","created_at":"2026-05-18T01:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.03324","created_at":"2026-05-18T01:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"4PHHS26EVX3T","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"4PHHS26EVX3TT4SS","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"4PHHS26E","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:884ec37fb4f7470f7ae4fc61c2ce7d2761d3e6537f03951dd338ee14d139617f","target":"graph","created_at":"2026-05-18T01:15:05Z","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"},"paper":{"abstract_excerpt":"Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet.\n  We propose a method for parsing a video into such semantic steps in an unsupervised way. Our method is capable of providing a semantic \"storyline\" of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. Our method ca","authors_text":"Amir Roshan Zamir, Ashutosh Saxena, Chenxia Wu, Ozan Sener, Silvio Savarese","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-11T08:22:06Z","title":"Unsupervised Semantic Action Discovery from Video Collections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.03324","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":"sha256:86f09b010ba2172ff61a9b1056a4b3c83b3ad7b6444c1d6d4803ed1d86755486","target":"record","created_at":"2026-05-18T01:15:05Z","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":"578c23b88bba3ae90cae857cbf498137c5670c6201781308be8df005af171184","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-11T08:22:06Z","title_canon_sha256":"2806b7dd355529767a3fcefb5ce182cf833e849164ca7439d5c5dcafe03d8fba"},"schema_version":"1.0","source":{"id":"1605.03324","kind":"arxiv","version":1}},"canonical_sha256":"e3ce796bc4adf739f252db139413495bf7f7e1b96ab94b0c145ae83b35598b97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3ce796bc4adf739f252db139413495bf7f7e1b96ab94b0c145ae83b35598b97","first_computed_at":"2026-05-18T01:15:05.652466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:15:05.652466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZEyPY7PA82iXIt4jdSaMggzPN3lEQF7G1/OF3sMa9uToHd3B8RqpeiL/bg4pUA24vdYy1d7tnW50N1JEB4M6CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:15:05.653065Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.03324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86f09b010ba2172ff61a9b1056a4b3c83b3ad7b6444c1d6d4803ed1d86755486","sha256:884ec37fb4f7470f7ae4fc61c2ce7d2761d3e6537f03951dd338ee14d139617f"],"state_sha256":"a126c2b1ac33807966ede9c19c5ad5bd706e69ac98e76ee2f9fc3d89c42fca61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g2NDStd6se83ZY6CXrkORMcsrmBT3w2ta5X4Lzcv9lSgqJAWvgjVOM260fphWiGOOOUkczaHxcnvqmpLxlZACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:20:31.062013Z","bundle_sha256":"6e0e9d7478e6cd58ab94b9c2f7dd56ea1ab6cf4fd7e6dae1bb78eaea13123ddd"}}